HARDWARE EXPLORER · SOURCE-GROUNDED ESTIMATES

How much memory do model weights need?

Explore estimated weight storage for BF16, FP8 and INT4. These are derived decimal-GB values, not observed GPU memory, inference speed or a promise of compatibility.

Evidence statusSource-first verified
Latest record check2026-11-19
Latest record full verification2026-11-19

VISUAL EXAMPLE · DERIVED, NOT BENCHMARKED

How precision changes weight memory.

One model, three mathematical weight-storage estimates. Lower precision reduces the estimated bytes required for weights; it does not establish that this model has released quantized files, supports every runtime, or fits in GPU memory during inference.

Inspect Qwen3-32B evidence →
BF16 / FP16~65.5 GB
FP8 / INT8~32.8 GB
INT4~16.4 GB

Qwen3-32B · decimal GB · excludes KV cache, activations and runtime overhead.

INTERACTIVE MEMORY EXPLORER

Find a model for your memory budget.

All model links are present in HTML. Filters and progressive loading enhance the experience when JavaScript is available.

820 matching models

Model / developerBF16 / FP16FP8 / INT8INT4
NVIDIA Nemotron 3 Nano 30B-A3BNVIDIA
~63.2 GB
~31.6 GB
~15.8 GB
Mistral Small 4 119B A6BMistral AI
~238.8 GB
~119.4 GB
~59.7 GB
Qwen3-32BQwen
~65.5 GB
~32.8 GB
~16.4 GB
DeepSeek-R1DeepSeek
~1,369.0 GB
~684.5 GB
~342.2 GB
gpt-oss-120bOpenAI
~233.7 GB
~116.8 GB
~58.4 GB
Gemma 3 27B ITGoogle
~54.9 GB
~27.4 GB
~13.7 GB
Llama 3.3 70B InstructMeta
~141.1 GB
~70.5 GB
~35.3 GB
Qwen-Image-2.1Qwen
~14.2 GB
~7.1 GB
~3.6 GB
Qwen3Guard-Stream-4BQwen
~8.1 GB
~4.0 GB
~2.0 GB
Qwen3Guard-Stream-0.6BQwen
~1.2 GB
~0.6 GB
~0.3 GB
Qwen3Guard-Stream-8BQwen
~15.2 GB
~7.6 GB
~3.8 GB
Qwen-Image-2.1-PE-I2IQwen
~18.8 GB
~9.4 GB
~4.7 GB
Qwen-Image-2.1-PE-T2IQwen
~18.8 GB
~9.4 GB
~4.7 GB
Qwen-Drive-1.0-4BQwen
~9.1 GB
~4.5 GB
~2.3 GB
Qwen3.8-Flash-Next-FP8Qwen
~360.0 GB
~180.0 GB
~90.0 GB
Qwen3.8-Flash-NextQwen
~360.0 GB
~180.0 GB
~90.0 GB
Qwen3.8-27BQwen
~55.6 GB
~27.8 GB
~13.9 GB
Qwen3.8-27B-FP8Qwen
~55.6 GB
~27.8 GB
~13.9 GB
Qwen3.8-2.4T-A95BQwen
~4,892.4 GB
~2,446.2 GB
~1,223.1 GB
Qwen3.8-2.4T-A95B-FP8Qwen
~4,892.4 GB
~2,446.2 GB
~1,223.1 GB
Qwen3-ASR-0.6B-hfQwen
~1.6 GB
~0.8 GB
~0.4 GB
Qwen3-ASR-1.7B-hfQwen
~4.1 GB
~2.0 GB
~1.0 GB
Qwen3-ForcedAligner-0.6B-hfQwen
~1.8 GB
~0.9 GB
~0.5 GB
Qwen-AgentWorld-35B-A3BQwen
~69.3 GB
~34.7 GB
~17.3 GB
Qwen-Image-BenchQwen
~54.7 GB
~27.4 GB
~13.7 GB
Qwen3.6-35B-A3B-FP8Qwen
~71.9 GB
~36.0 GB
~18.0 GB
Qwen3.6-27B-FP8Qwen
~55.6 GB
~27.8 GB
~13.9 GB
Qwen3.6-27BQwen
~55.6 GB
~27.8 GB
~13.9 GB
Qwen3.5-35B-A3B-GPTQ-Int4Qwen
~71.9 GB
~36.0 GB
~18.0 GB
Qwen3.5-27B-GPTQ-Int4Qwen
~55.6 GB
~27.8 GB
~13.9 GB
Qwen3.5-35B-A3B-FP8Qwen
~71.9 GB
~36.0 GB
~18.0 GB
Qwen3.5-27B-FP8Qwen
~55.6 GB
~27.8 GB
~13.9 GB
Qwen3.5-35B-A3BQwen
~71.9 GB
~36.0 GB
~18.0 GB
Qwen3.5-9B-BaseQwen
~19.3 GB
~9.7 GB
~4.8 GB
Qwen3.5-35B-A3B-BaseQwen
~71.9 GB
~36.0 GB
~18.0 GB
Qwen3.5-0.8B-BaseQwen
~1.8 GB
~0.9 GB
~0.4 GB
Qwen3.5-2B-BaseQwen
~4.5 GB
~2.3 GB
~1.1 GB
Qwen3.5-4B-BaseQwen
~9.3 GB
~4.7 GB
~2.3 GB
Qwen3-Embedding-0.6BQwen
~1.2 GB
~0.6 GB
~0.3 GB
Qwen3-Reranker-8BQwen
~16.4 GB
~8.2 GB
~4.1 GB
Qwen3-Reranker-4BQwen
~8.0 GB
~4.0 GB
~2.0 GB
Qwen3-Reranker-0.6BQwen
~1.2 GB
~0.6 GB
~0.3 GB
Mistral-Large-3-675B-Instruct-2512-NVFP4Mistral AI
~1,350.0 GB
~675.0 GB
~337.5 GB
Shieldstral-1.0-3BMistral AI
~7.7 GB
~3.9 GB
~1.9 GB
Leanstral-1.5-119B-A6BMistral AI
~238.0 GB
~119.0 GB
~59.5 GB
Mistral-Small-4-119B-2603-eagleMistral AI
~238.0 GB
~119.0 GB
~59.5 GB
Mistral-Medium-3.5-128BMistral AI
~255.4 GB
~127.7 GB
~63.9 GB
Mistral-Large-3-675B-Instruct-2512-EagleMistral AI
~1,350.0 GB
~675.0 GB
~337.5 GB
Mistral-Large-3-675B-Instruct-2512Mistral AI
~1,350.0 GB
~675.0 GB
~337.5 GB
Ministral-3-8B-Reasoning-2512Mistral AI
~17.8 GB
~8.9 GB
~4.5 GB
Ministral-3-8B-Instruct-2512-BF16Mistral AI
~17.8 GB
~8.9 GB
~4.5 GB
Ministral-3-8B-Instruct-2512Mistral AI
~17.8 GB
~8.9 GB
~4.5 GB
Ministral-3-3B-Reasoning-2512Mistral AI
~8.5 GB
~4.2 GB
~2.1 GB
Ministral-3-3B-Instruct-2512-BF16Mistral AI
~8.5 GB
~4.2 GB
~2.1 GB
Ministral-3-3B-Instruct-2512Mistral AI
~7.7 GB
~3.9 GB
~1.9 GB
Ministral-3-14B-Reasoning-2512Mistral AI
~27.9 GB
~13.9 GB
~7.0 GB
Ministral-3-14B-Instruct-2512-BF16Mistral AI
~27.9 GB
~13.9 GB
~7.0 GB
Ministral-3-14B-Instruct-2512Mistral AI
~27.9 GB
~13.9 GB
~7.0 GB
Leanstral-2603Mistral AI
—
—
—
Devstral-Small-2-24B-Instruct-2512Mistral AI
~48.0 GB
~24.0 GB
~12.0 GB
Devstral-2-123B-Instruct-2512Mistral AI
~250.1 GB
~125.0 GB
~62.5 GB
Pixtral-Large-Instruct-2411Mistral AI
—
—
—
Pixtral-12B-2409Mistral AI
~24.0 GB
~12.0 GB
~6.0 GB
Mistral-Medium-3.5-128B-EAGLEMistral AI
~256.0 GB
~128.0 GB
~64.0 GB
Voxtral-4B-TTS-2603Mistral AI
~8.0 GB
~4.0 GB
~2.0 GB
Voxtral-Mini-4B-Realtime-2602Mistral AI
~8.9 GB
~4.4 GB
~2.2 GB
Magistral-Small-2509Mistral AI
~48.0 GB
~24.0 GB
~12.0 GB
Ministral-3-3B-Instruct-2512-ONNXMistral AI
~8.0 GB
~4.0 GB
~2.0 GB
Ministral-3-3B-Reasoning-2512-GGUFMistral AI
~6.0 GB
~3.0 GB
~1.5 GB
Ministral-3-8B-Reasoning-2512-GGUFMistral AI
~16.0 GB
~8.0 GB
~4.0 GB
Ministral-3-3B-Instruct-2512-GGUFMistral AI
~6.0 GB
~3.0 GB
~1.5 GB
Ministral-3-8B-Instruct-2512-GGUFMistral AI
~16.0 GB
~8.0 GB
~4.0 GB
Ministral-3-14B-Instruct-2512-GGUFMistral AI
~28.0 GB
~14.0 GB
~7.0 GB
Ministral-3-3B-Base-2512Mistral AI
~8.5 GB
~4.2 GB
~2.1 GB
Ministral-3-8B-Base-2512Mistral AI
~17.8 GB
~8.9 GB
~4.5 GB
Ministral-3-14B-Base-2512Mistral AI
~27.9 GB
~13.9 GB
~7.0 GB
Mistral-Small-3.2-24B-Instruct-2506Mistral AI
~48.0 GB
~24.0 GB
~12.0 GB
Prompt-Guard-86MMeta
~0.6 GB
~0.3 GB
~0.1 GB
Meta-Llama-3-8B-InstructMeta
~16.1 GB
~8.0 GB
~4.0 GB
Meta-Llama-3-70B-InstructMeta
~141.1 GB
~70.5 GB
~35.3 GB
Llama-4-Maverick-17B-128E-InstructMeta
~803.2 GB
~401.6 GB
~200.8 GB
Llama-4-Maverick-17B-128E-Instruct-FP8Meta
~803.3 GB
~401.6 GB
~200.8 GB
Llama-4-Scout-17B-16E-InstructMeta
~217.3 GB
~108.6 GB
~54.3 GB
Llama-4-Maverick-17B-128E-Instruct-OriginalMeta
~804.0 GB
~402.0 GB
~201.0 GB
Llama-Guard-4-12BMeta
~24.0 GB
~12.0 GB
~6.0 GB
Llama-Prompt-Guard-2-86MMeta
~0.6 GB
~0.3 GB
~0.1 GB
Llama-Prompt-Guard-2-22MMeta
~0.1 GB
~0.1 GB
~0.0 GB
Llama-4-Maverick-17B-128EMeta
~803.2 GB
~401.6 GB
~200.8 GB
Llama-4-Scout-17B-16EMeta
~217.3 GB
~108.6 GB
~54.3 GB
Llama-4-Maverick-17B-128E-OriginalMeta
~804.0 GB
~402.0 GB
~201.0 GB
Llama-4-Scout-17B-16E-OriginalMeta
~218.0 GB
~109.0 GB
~54.5 GB
Llama-4-Maverick-17B-128E-Instruct-FP8-OriginalMeta
~804.0 GB
~402.0 GB
~201.0 GB
Llama-4-Scout-17B-16E-Instruct-OriginalMeta
~218.0 GB
~109.0 GB
~54.5 GB
Llama-3.2-90B-Vision-InstructMeta
~177.2 GB
~88.6 GB
~44.3 GB
Llama-3.1-70B-InstructMeta
~141.1 GB
~70.5 GB
~35.3 GB
Llama-3.1-405B-FP8Meta
~811.7 GB
~405.9 GB
~202.9 GB
Llama-3.2-11B-Vision-InstructMeta
~21.3 GB
~10.7 GB
~5.3 GB
Llama-3.2-3B-Instruct-QLORA_INT4_EO8Meta
~6.0 GB
~3.0 GB
~1.5 GB
Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8Meta
~6.0 GB
~3.0 GB
~1.5 GB
Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8Meta
~2.0 GB
~1.0 GB
~0.5 GB
Llama-3.2-1B-Instruct-QLORA_INT4_EO8Meta
~2.0 GB
~1.0 GB
~0.5 GB
Llama-Guard-3-11B-VisionMeta
~21.3 GB
~10.7 GB
~5.3 GB
Llama-3.2-1BMeta
~2.5 GB
~1.2 GB
~0.6 GB
Llama-3.2-1B-InstructMeta
~2.5 GB
~1.2 GB
~0.6 GB
Llama-3.2-3BMeta
~6.4 GB
~3.2 GB
~1.6 GB
Llama-3.2-3B-InstructMeta
~6.4 GB
~3.2 GB
~1.6 GB
Llama-3.1-8BMeta
~16.1 GB
~8.0 GB
~4.0 GB
all-MiniLM-L6-v2Sentence Transformers
~0.1 GB
~0.0 GB
~0.0 GB
ms-marco-MiniLM-L6-v2cross-encoder
~0.1 GB
~0.0 GB
~0.0 GB
paraphrase-multilingual-MiniLM-L12-v2Sentence Transformers
~0.2 GB
~0.1 GB
~0.1 GB
bert-base-uncasedgoogle-bert
~0.2 GB
~0.1 GB
~0.1 GB
bge-small-en-v1.5BAAI
~0.1 GB
~0.0 GB
~0.0 GB
bge-m3BAAI
—
—
—
MiniMax-H3Comfy-Org
—
—
—
Qwen3-0.6BQwen
~1.5 GB
~0.8 GB
~0.4 GB
electra-base-discriminatorGoogle
—
—
—
gpt2openai-community
~0.3 GB
~0.1 GB
~0.1 GB
clip-vit-base-patch32OpenAI
—
—
—
t5-smallgoogle-t5
~0.1 GB
~0.1 GB
~0.0 GB
all-mpnet-base-v2Sentence Transformers
~0.2 GB
~0.1 GB
~0.1 GB
chronos-2amazon
~0.2 GB
~0.1 GB
~0.1 GB
Kokoro-82Mhexgrad
—
—
—
bge-reranker-v2-m3BAAI
~1.1 GB
~0.6 GB
~0.3 GB
gemma-4-31B-itGoogle
~62.5 GB
~31.3 GB
~15.6 GB
gemma-4-26B-A4B-itGoogle
~51.6 GB
~25.8 GB
~12.9 GB
xlm-roberta-baseFacebookAI
~0.6 GB
~0.3 GB
~0.1 GB
nomic-embed-text-v1.5nomic-ai
~0.3 GB
~0.1 GB
~0.1 GB
Qwen3-VL-8B-InstructQwen
~17.5 GB
~8.8 GB
~4.4 GB
Qwen3-8BQwen
~16.4 GB
~8.2 GB
~4.1 GB
Qwen3.5-9BQwen
~19.3 GB
~9.7 GB
~4.8 GB
mobilenetv3_small_100.lamb_in1ktimm
~0.0 GB
~0.0 GB
~0.0 GB
Llama-3.1-8B-InstructMeta
~16.1 GB
~8.0 GB
~4.0 GB
Qwen2.5-7B-InstructQwen
~15.2 GB
~7.6 GB
~3.8 GB
clip-vit-large-patch14OpenAI
~0.9 GB
~0.4 GB
~0.2 GB
vit-base-patch16-224Google
~0.2 GB
~0.1 GB
~0.0 GB
gpt-oss-20bOpenAI
~41.8 GB
~20.9 GB
~10.5 GB
z_image_turboComfy-Org
—
—
—
XTTS-v2coqui
—
—
—
multilingual-e5-smallintfloat
~0.2 GB
~0.1 GB
~0.1 GB
Krea-2Comfy-Org
—
—
—
GLM-5.3-FlashZ.ai
~642.6 GB
~321.3 GB
~160.7 GB
distilbert-base-uncaseddistilbert
~0.1 GB
~0.1 GB
~0.0 GB
adetailerBingsu
—
—
—
whisper-large-v3-turboOpenAI
~1.6 GB
~0.8 GB
~0.4 GB
bge-large-en-v1.5BAAI
~0.7 GB
~0.3 GB
~0.2 GB
multilingual-e5-largeintfloat
~1.1 GB
~0.6 GB
~0.3 GB
Qwen3.5-4BQwen
~9.3 GB
~4.7 GB
~2.3 GB
whisperkit-coremlargmaxinc
—
—
—
DeepSeek-V4-Flash-0731DeepSeek
~608.4 GB
~304.2 GB
~152.1 GB
paraphrase-multilingual-mpnet-base-v2Sentence Transformers
~0.6 GB
~0.3 GB
~0.1 GB
stable-diffusion-xl-base-1.0Stability AI
~5.1 GB
~2.6 GB
~1.3 GB
bge-base-en-v1.5BAAI
~0.2 GB
~0.1 GB
~0.1 GB
wav2vec2-large-xlsr-53-japanesejonatasgrosman
—
—
—
Wan_2.2_ComfyUI_RepackagedComfy-Org
—
—
—
Qwen-Image-2.1Comfy-Org
—
—
—
Qwen2.5-0.5B-InstructQwen
~1.0 GB
~0.5 GB
~0.2 GB
MiniMax-H3MiniMax
~66.2 GB
~33.1 GB
~16.6 GB
whisper-large-v3OpenAI
~3.1 GB
~1.5 GB
~0.8 GB
speaker-diarization-community-1pyannote
—
—
—
roberta-baseFacebookAI
~0.2 GB
~0.1 GB
~0.1 GB
Qwen3-4BQwen
~8.0 GB
~4.0 GB
~2.0 GB
Qwen2.5-1.5B-InstructQwen
~3.1 GB
~1.5 GB
~0.8 GB
Qwen2.5-VL-7B-InstructQwen
~16.6 GB
~8.3 GB
~4.2 GB
segmentation-3.0pyannote
—
—
—
Qwen3.6-35B-A3B-NVFP4NVIDIA
~37.4 GB
~18.7 GB
~9.3 GB
gemma-4-E4B-itGoogle
~16.0 GB
~8.0 GB
~4.0 GB
multilingual-e5-baseintfloat
~0.6 GB
~0.3 GB
~0.1 GB
Qwen3.6-35B-A3BQwen
~71.9 GB
~36.0 GB
~18.0 GB
clap-htsat-fusedlaion
~0.3 GB
~0.1 GB
~0.1 GB
opt-125mMeta
—
—
—
finbertProsusAI
~0.2 GB
~0.1 GB
~0.1 GB
tiny-Qwen2ForCausalLM-2.5trl-internal-testing
~0.0 GB
~0.0 GB
~0.0 GB
embeddinggemma-300mGoogle
~0.6 GB
~0.3 GB
~0.1 GB
DeepSeek-V3.2DeepSeek
~1,370.7 GB
~685.4 GB
~342.7 GB
ModernBERT-baseanswerdotai
~0.3 GB
~0.1 GB
~0.1 GB
Wan_2.1_ComfyUI_repackagedComfy-Org
—
—
—
contrieverMeta
—
—
—
roberta-largeFacebookAI
~0.7 GB
~0.4 GB
~0.2 GB
Qwen3.5-2BQwen
~4.5 GB
~2.3 GB
~1.1 GB
mdeberta-v3-baseMicrosoft
—
—
—
wespeaker-voxceleb-resnet34-LMpyannote
—
—
—
Qwen3-4B-Instruct-2507Qwen
~8.0 GB
~4.0 GB
~2.0 GB
gemma-4-E2B-itGoogle
~10.2 GB
~5.1 GB
~2.6 GB
Qwen2.5-3B-InstructQwen
~6.2 GB
~3.1 GB
~1.5 GB
gemma-3-1b-itGoogle
~2.0 GB
~1.0 GB
~0.5 GB
LTX-2.5Lightricks
—
—
—
Kimi-K3-DSparkRadixArk
~4.5 GB
~2.2 GB
~1.1 GB
sam3Meta
~1.7 GB
~0.9 GB
~0.4 GB
Mistral-7B-Instruct-v0.3Mistral AI
~14.5 GB
~7.2 GB
~3.6 GB
bart-large-mnliMeta
~0.8 GB
~0.4 GB
~0.2 GB
Kimi-K3Moonshot AI
~5,559.9 GB
~2,779.9 GB
~1,390.0 GB
Qwen3-TTS-12Hz-1.7B-CustomVoiceQwen
~3.8 GB
~1.9 GB
~1.0 GB
Qwen3-TTS-12Hz-1.7B-BaseQwen
~3.9 GB
~1.9 GB
~1.0 GB
DeepSeek-OCRDeepSeek
~6.7 GB
~3.3 GB
~1.7 GB
chronos-2autogluon
~0.2 GB
~0.1 GB
~0.1 GB
chronos-bolt-smallamazon
~0.1 GB
~0.1 GB
~0.0 GB
stable-diffusion-v1-5-archiveComfy-Org
—
—
—
distilbert-base-uncased-finetuned-sst-2-englishdistilbert
~0.1 GB
~0.1 GB
~0.0 GB
all-MiniLM-L12-v2Sentence Transformers
~0.1 GB
~0.0 GB
~0.0 GB
moondream2vikhyatk
~3.9 GB
~1.9 GB
~1.0 GB
roberta-base-go_emotionsSamLowe
~0.2 GB
~0.1 GB
~0.1 GB
GLM-OCRZ.ai
~2.6 GB
~1.3 GB
~0.7 GB
Qwen3-VL-4B-InstructQwen
~8.9 GB
~4.4 GB
~2.2 GB
nomic-embed-text-v1nomic-ai
~0.3 GB
~0.1 GB
~0.1 GB
whisper-smallOpenAI
~0.5 GB
~0.2 GB
~0.1 GB
Qwen-Image_ComfyUIComfy-Org
—
—
—
granite-embedding-small-english-r2IBM
~0.1 GB
~0.1 GB
~0.0 GB
Unlimited-OCRbaidu
~6.7 GB
~3.3 GB
~1.7 GB
bge-reranker-baseBAAI
~0.6 GB
~0.3 GB
~0.1 GB
gemma-4-12B-itGoogle
~23.9 GB
~12.0 GB
~6.0 GB
chronos-bolt-smallautogluon
~0.1 GB
~0.1 GB
~0.0 GB
Qwen3-1.7BQwen
~4.1 GB
~2.0 GB
~1.0 GB
bert-base-casedgoogle-bert
~0.2 GB
~0.1 GB
~0.1 GB
Qwen3.5-0.8BQwen
~1.8 GB
~0.9 GB
~0.4 GB
bge-small-zh-v1.5BAAI
~0.1 GB
~0.0 GB
~0.0 GB
twitter-roberta-base-sentiment-latestcardiffnlp
—
—
—
Qwen3-14BQwen
~29.5 GB
~14.8 GB
~7.4 GB
nsfw_image_detectionFalconsai
~0.2 GB
~0.1 GB
~0.0 GB
Mistral-7B-Instruct-v0.2Mistral AI
~14.5 GB
~7.2 GB
~3.6 GB
Qwen3-Embedding-8BQwen
~15.1 GB
~7.6 GB
~3.8 GB
jina-embeddings-v3jinaai
~1.1 GB
~0.6 GB
~0.3 GB
wav2vec2-large-xlsr-53-portuguesejonatasgrosman
—
—
—
Qwen3.8-27B-NVFP4unsloth
~39.7 GB
~19.9 GB
~9.9 GB
Florence-2-baseMicrosoft
~0.5 GB
~0.2 GB
~0.1 GB
chatterboxResembleAI
—
—
—
Qwen3-VL-2B-InstructQwen
~4.3 GB
~2.1 GB
~1.1 GB
xlm-roberta-largeFacebookAI
~1.1 GB
~0.6 GB
~0.3 GB
GLM-4.7-FlashZ.ai
~62.4 GB
~31.2 GB
~15.6 GB
Qwen2.5-Coder-7B-InstructQwen
~15.2 GB
~7.6 GB
~3.8 GB
ms-marco-MiniLM-L4-v2cross-encoder
~0.0 GB
~0.0 GB
~0.0 GB
GLM-5.3Z.ai
~1,506.7 GB
~753.3 GB
~376.7 GB
Qwen3.5-27BQwen
~55.6 GB
~27.8 GB
~13.9 GB
WanVideo_comfyKijai
—
—
—
dolphin-2.9.1-yi-1.5-34bdphn
~68.8 GB
~34.4 GB
~17.2 GB
deberta-v3-baseMicrosoft
—
—
—
DeepSeek-V3DeepSeek
~1,369.1 GB
~684.5 GB
~342.3 GB
all-MiniLM-L6-v2Xenova
—
—
—
Qwen2.5-VL-3B-InstructQwen
~7.5 GB
~3.8 GB
~1.9 GB
t5-basegoogle-t5
~0.5 GB
~0.2 GB
~0.1 GB
mxbai-embed-large-v1mixedbread-ai
~0.7 GB
~0.3 GB
~0.2 GB
CLIP-ViT-B-32-laion2B-s34B-b79Klaion
~0.3 GB
~0.1 GB
~0.1 GB
wav2vec2-large-xlsr-53-russianjonatasgrosman
—
—
—
TRELLIS.2-4BMicrosoft
—
—
—
chandra-ocr-2datalab-to
~10.6 GB
~5.3 GB
~2.6 GB
Animacirclestone-labs
—
—
—
DeepSeek-V3-0324DeepSeek
~1,369.1 GB
~684.5 GB
~342.3 GB
Minimax-h3-Turbolightx2v
—
—
—
TRELLIS-image-largeMicrosoft
—
—
—
bge-reranker-largeBAAI
~1.1 GB
~0.6 GB
~0.3 GB
OmniVoicek2-fsa
~1.2 GB
~0.6 GB
~0.3 GB
Bio_ClinicalBERTemilyalsentzer
—
—
—
dinov2-baseMeta
~0.2 GB
~0.1 GB
~0.0 GB
distilgpt2distilbert
~0.2 GB
~0.1 GB
~0.0 GB
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA
~8.0 GB
~4.0 GB
~2.0 GB
stable-diffusion-v1-5stable-diffusion-v1-5
~1.7 GB
~0.9 GB
~0.4 GB
timesfm-3.0-pytorchGoogle
~0.7 GB
~0.3 GB
~0.2 GB
bert-base-chinesegoogle-bert
~0.2 GB
~0.1 GB
~0.1 GB
Qwen-Image-Edit_ComfyUIComfy-Org
—
—
—
Gemma-4-E4B-Uncensored-HauhauCS-AggressiveHauhauCS
—
—
—
bert-base-multilingual-uncasedgoogle-bert
~0.3 GB
~0.2 GB
~0.1 GB
Qwen3-ASR-1.7BQwen
~4.7 GB
~2.4 GB
~1.2 GB
esm2_t33_650M_UR50DMeta
~1.3 GB
~0.7 GB
~0.3 GB
nemotron-3.5-asr-streaming-0.6bNVIDIA
~1.3 GB
~0.6 GB
~0.3 GB
MiniCPM5-2Bopenbmb
~5.0 GB
~2.5 GB
~1.3 GB
LTX-2.3Lightricks
—
—
—
FLUX.1-devBlack Forest Labs
~23.8 GB
~11.9 GB
~6.0 GB
TinyLlama-1.1B-Chat-v1.0TinyLlama
~2.2 GB
~1.1 GB
~0.6 GB
spkrec-ecapa-voxcelebspeechbrain
—
—
—
Qwen3.6-35B-A3B-Uncensored-HauhauCS-AggressiveHauhauCS
—
—
—
faster-whisper-smallSystran
—
—
—
bart-large-cnnMeta
~0.8 GB
~0.4 GB
~0.2 GB
DeepSeek-V4-FlashDeepSeek
~581.9 GB
~290.9 GB
~145.5 GB
Gemma-4-31B-IT-NVFP4NVIDIA
~41.7 GB
~20.9 GB
~10.4 GB
fashion-clippatrickjohncyh
~0.3 GB
~0.1 GB
~0.1 GB
DeepSeek-V4.1-FlashDeepSeek
~1,526.4 GB
~763.2 GB
~381.6 GB
clip-vit-large-patch14-336OpenAI
—
—
—
bert-base-multilingual-casedgoogle-bert
~0.4 GB
~0.2 GB
~0.1 GB
mms-300m-1130-forced-alignerMahmoudAshraf
~0.6 GB
~0.3 GB
~0.2 GB
blip-image-captioning-baseSalesforce
—
—
—
Qwen3-30B-A3BQwen
~61.1 GB
~30.5 GB
~15.3 GB
gemma-3-4b-itGoogle
~8.6 GB
~4.3 GB
~2.1 GB
Ornith-1.0-35Bornith-ai
~0.0 GB
~0.0 GB
~0.0 GB
Qwen2.5-32B-InstructQwen
~65.5 GB
~32.8 GB
~16.4 GB
SmolLM2-135M-InstructHuggingFaceTB
~0.3 GB
~0.1 GB
~0.1 GB
GLM-5.2Z.ai
~1,506.7 GB
~753.3 GB
~376.7 GB
pythia-160mEleutherAI
~0.4 GB
~0.2 GB
~0.1 GB
xlm-roberta-large-xnlijoeddav
~1.1 GB
~0.6 GB
~0.3 GB
CLIP-ViT-L-14-laion2B-s32B-b82Klaion
~0.9 GB
~0.4 GB
~0.2 GB
dinov2-smallMeta
~0.0 GB
~0.0 GB
~0.0 GB
bert-base-NERdslim
~0.2 GB
~0.1 GB
~0.1 GB
Qwen3-VL-Embedding-8BQwen
~16.3 GB
~8.1 GB
~4.1 GB
Qwen3-Embedding-4BQwen
~8.0 GB
~4.0 GB
~2.0 GB
vit-base-patch16-224-in21kGoogle
~0.2 GB
~0.1 GB
~0.0 GB
sdxl-turboStability AI
~5.1 GB
~2.6 GB
~1.3 GB
wav2vec2-base-960hMeta
~0.2 GB
~0.1 GB
~0.1 GB
MiniMax-M2.7MiniMax
~457.4 GB
~228.7 GB
~114.3 GB
multilingual-e5-large-instructintfloat
~1.1 GB
~0.6 GB
~0.3 GB
dots.ocrdots-studio
~6.1 GB
~3.0 GB
~1.5 GB
colbertv2.0colbert-ir
~0.2 GB
~0.1 GB
~0.1 GB
whisper-baseOpenAI
~0.1 GB
~0.1 GB
~0.0 GB
Inklingthinkingmachines
~1,904.8 GB
~952.4 GB
~476.2 GB
Qwen2.5-14B-InstructQwen
~29.5 GB
~14.8 GB
~7.4 GB
mmarco-mMiniLMv2-L12-H384-v1cross-encoder
~0.2 GB
~0.1 GB
~0.1 GB
flux1-devComfy-Org
—
—
—
Qwen2.5-0.5BQwen
~1.0 GB
~0.5 GB
~0.2 GB
wav2vec2-baseMeta
—
—
—
stable-diffusion-v1-4CompVis
~1.7 GB
~0.9 GB
~0.4 GB
siglip2-base-patch16-256Google
~0.8 GB
~0.4 GB
~0.2 GB
Qwen2-VL-2B-InstructQwen
~4.4 GB
~2.2 GB
~1.1 GB
SmolLM2-135MHuggingFaceTB
~0.3 GB
~0.1 GB
~0.1 GB
musicgen-mediumMeta
—
—
—
chronos-2-smallautogluon
~0.1 GB
~0.0 GB
~0.0 GB
NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA
~247.2 GB
~123.6 GB
~61.8 GB
siglip-so400m-patch14-384Google
~1.8 GB
~0.9 GB
~0.4 GB
llava-1.5-7b-hfllava-hf
~14.1 GB
~7.1 GB
~3.5 GB
owlv2-base-patch16-ensembleGoogle
~0.3 GB
~0.1 GB
~0.1 GB
flan-t5-baseGoogle
~0.5 GB
~0.2 GB
~0.1 GB
DeepSeek-R1-Distill-Qwen-1.5BDeepSeek
~3.5 GB
~1.8 GB
~0.9 GB
gte-multilingual-baseAlibaba-NLP
~0.6 GB
~0.3 GB
~0.1 GB
Qwen2.5-Coder-32B-InstructQwen
~65.5 GB
~32.8 GB
~16.4 GB
FLUX.1-schnellBlack Forest Labs
~23.8 GB
~11.9 GB
~6.0 GB
gemma-2-9b-itGoogle
~18.5 GB
~9.2 GB
~4.6 GB
ms-marco-MiniLM-L12-v2cross-encoder
~0.1 GB
~0.0 GB
~0.0 GB
OTel-2.0-LLM-31B-ITfarbodtavakkoli
~62.5 GB
~31.3 GB
~15.6 GB
w2v-bert-2.0Meta
~1.2 GB
~0.6 GB
~0.3 GB
all-distilroberta-v1Sentence Transformers
~0.2 GB
~0.1 GB
~0.0 GB
Depth-Anything-V2-Small-hfdepth-anything
~0.1 GB
~0.0 GB
~0.0 GB
Kronos-Tokenizer-baseNeoQuasar
~0.0 GB
~0.0 GB
~0.0 GB
DeepSeek-V4-Flash-Vision-ExpDeepSeek
~609.3 GB
~304.6 GB
~152.3 GB
flux2-devComfy-Org
—
—
—
Z-Image-TurboTongyi-MAI
~12.3 GB
~6.2 GB
~3.1 GB
timesfm-2.5-200m-pytorchGoogle
~0.5 GB
~0.2 GB
~0.1 GB
HunyuanOCRTencent
~2.2 GB
~1.1 GB
~0.6 GB
Qwen3-VL-Embedding-2BQwen
~4.3 GB
~2.1 GB
~1.1 GB
wav2vec2-large-robust-24-ft-age-genderaudeering
~0.6 GB
~0.3 GB
~0.2 GB
VibeVoice-1.5BMicrosoft
~5.4 GB
~2.7 GB
~1.4 GB
Qwen2.5-Coder-14B-InstructQwen
~29.5 GB
~14.8 GB
~7.4 GB
Llama-2-7b-hfMeta
~13.5 GB
~6.7 GB
~3.4 GB
MiniCPM-o-4_5openbmb
~18.7 GB
~9.4 GB
~4.7 GB
grounding-dino-baseIDEA-Research
~0.5 GB
~0.2 GB
~0.1 GB
Qwen3.8-27B-OBLITERATEDOBLITERATUS
~55.6 GB
~27.8 GB
~13.9 GB
LTX-VideoLightricks
~3.9 GB
~1.9 GB
~1.0 GB
FastVideo-FastH3-4-step-Preview-v1-VSA-DataFreeFastVideo
~70.1 GB
~35.0 GB
~17.5 GB
gte-reranker-modernbert-baseAlibaba-NLP
~0.3 GB
~0.1 GB
~0.1 GB
NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4NVIDIA
~36.5 GB
~18.2 GB
~9.1 GB
medgemma-4b-itGoogle
~8.6 GB
~4.3 GB
~2.1 GB
Qwen3-VL-8B-Instruct-FP8Qwen
~17.5 GB
~8.8 GB
~4.4 GB
parakeet-tdt-0.6b-v3mlx-community
~1.2 GB
~0.6 GB
~0.3 GB
Ornith-1.0-9Bornith-ai
~0.0 GB
~0.0 GB
~0.0 GB
nomic-embed-text-v2-moenomic-ai
~0.9 GB
~0.5 GB
~0.2 GB
docling-modelsdocling-project
—
—
—
whisper-tinyOpenAI
~0.1 GB
~0.0 GB
~0.0 GB
phi-2Microsoft
~5.6 GB
~2.8 GB
~1.4 GB
siglip-base-patch16-224Google
~0.4 GB
~0.2 GB
~0.1 GB
F5-TTSSWivid
—
—
—
distilroberta-basedistilbert
~0.2 GB
~0.1 GB
~0.0 GB
siglip2-base-patch16-224Google
~0.8 GB
~0.4 GB
~0.2 GB
DeepSeek-OCR-2DeepSeek
~6.8 GB
~3.4 GB
~1.7 GB
text2vec-base-chineseshibing624
~0.2 GB
~0.1 GB
~0.1 GB
multi-qa-mpnet-base-dot-v1Sentence Transformers
~0.2 GB
~0.1 GB
~0.1 GB
faster-whisper-large-v3Systran
—
—
—
gpt2-largeopenai-community
~1.6 GB
~0.8 GB
~0.4 GB
Qwen3-30B-A3B-Instruct-2507Qwen
~61.1 GB
~30.5 GB
~15.3 GB
VibeVoice-ASRMicrosoft
~17.4 GB
~8.7 GB
~4.3 GB
faster-whisper-tinySystran
—
—
—
surya-ocr-2datalab-to
~1.4 GB
~0.7 GB
~0.3 GB
Gemma4-12B-QAT-Uncensored-HauhauCS-BalancedHauhauCS
—
—
—
DeepSeek-V4-ProDeepSeek
~3,197.7 GB
~1,598.8 GB
~799.4 GB
bge-base-enBAAI
~0.2 GB
~0.1 GB
~0.1 GB
bge-base-en-v1.5-course-recommender-v5datasocietyco
~0.2 GB
~0.1 GB
~0.1 GB
Qwen-72BQwen
~144.6 GB
~72.3 GB
~36.1 GB
nllb-200-distilled-600MMeta
—
—
—
wav2vec2-large-xlsr-53-chinese-zh-cnjonatasgrosman
—
—
—
e5-large-v2intfloat
~0.7 GB
~0.3 GB
~0.2 GB
indonesian-roberta-base-posp-taggerw11wo
~0.2 GB
~0.1 GB
~0.1 GB
docling-layout-herondocling-project
~0.1 GB
~0.0 GB
~0.0 GB
layoutlmv3-baseMicrosoft
~0.2 GB
~0.1 GB
~0.1 GB
clip-vit-base-patch16OpenAI
—
—
—
DeepSeek-Coder-V2-Lite-InstructDeepSeek
~31.4 GB
~15.7 GB
~7.8 GB
Qwen3.6-27B-NVFP4unsloth
~42.5 GB
~21.2 GB
~10.6 GB
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4NVIDIA
~35.6 GB
~17.8 GB
~8.9 GB
parrot_paraphraser_on_T5prithivida
—
—
—
ast-finetuned-audioset-10-10-0.4593MIT
~0.2 GB
~0.1 GB
~0.0 GB
finbert-toneyiyanghkust
—
—
—
Phi-3.5-vision-instructMicrosoft
~8.3 GB
~4.2 GB
~2.1 GB
Cosmos3-EdgeNVIDIA
~7.7 GB
~3.9 GB
~1.9 GB
gte-large-en-v1.5Alibaba-NLP
~0.9 GB
~0.4 GB
~0.2 GB
paraphrase-MiniLM-L6-v2Sentence Transformers
~0.1 GB
~0.0 GB
~0.0 GB
legal-bert-base-uncasednlpaueb
—
—
—
Qwen3.6-35B-A3B-NVFP4RedHatAI
~69.3 GB
~34.7 GB
~17.3 GB
Qwen3-Coder-NextQwen
~159.3 GB
~79.7 GB
~39.8 GB
siglip2-giant-opt-patch16-384Google
~3.7 GB
~1.9 GB
~0.9 GB
SmolVLM2-500M-Video-InstructHuggingFaceTB
~1.0 GB
~0.5 GB
~0.2 GB
Qwen3.8-27B-NVFP4RadixArk
~36.3 GB
~18.2 GB
~9.1 GB
pubmedbert-base-embeddingsNeuML
~0.2 GB
~0.1 GB
~0.1 GB
table-transformer-structure-recognitionMicrosoft
~0.1 GB
~0.0 GB
~0.0 GB
diffusiongemma-26B-A4B-itGoogle
~51.6 GB
~25.8 GB
~12.9 GB
jina-reranker-v2-base-multilingualjinaai
~0.6 GB
~0.3 GB
~0.1 GB
parakeet-tdt-0.6b-v3NVIDIA
~1.2 GB
~0.6 GB
~0.3 GB
Gemma-4-26B-A4B-NVFP4NVIDIA
~28.8 GB
~14.4 GB
~7.2 GB
esmfold_v1Meta
—
—
—
Qwen3-Coder-Next-FP8Qwen
~159.4 GB
~79.7 GB
~39.8 GB
BiRefNetZhengPeng7
~0.4 GB
~0.2 GB
~0.1 GB
DeepSeek-R1-0528-Qwen3-8BDeepSeek
~16.4 GB
~8.2 GB
~4.1 GB
VoxCPM2openbmb
~4.6 GB
~2.3 GB
~1.1 GB
chronos-t5-smallamazon
~0.1 GB
~0.1 GB
~0.0 GB
turn-detectorlivekit
~0.3 GB
~0.1 GB
~0.1 GB
paraphrase-mpnet-base-v2Sentence Transformers
~0.2 GB
~0.1 GB
~0.1 GB
SapBERT-from-PubMedBERT-fulltextcambridgeltl
~0.2 GB
~0.1 GB
~0.1 GB
GOT-OCR2_0stepfun-ai
~1.4 GB
~0.7 GB
~0.4 GB
phi-4Microsoft
~29.3 GB
~14.7 GB
~7.3 GB
Qwen3-Coder-30B-A3B-Instruct-FP8Qwen
~61.1 GB
~30.5 GB
~15.3 GB
Llama-2-7b-chat-hfMeta
~13.5 GB
~6.7 GB
~3.4 GB
Qwen3-TTS-12Hz-0.6B-CustomVoiceQwen
~1.8 GB
~0.9 GB
~0.5 GB
distiluse-base-multilingual-cased-v1Sentence Transformers
~0.3 GB
~0.1 GB
~0.1 GB
manga-ocr-basekha-white
—
—
—
dinov3-vitl16-pretrain-lvd1689mMeta
~0.6 GB
~0.3 GB
~0.1 GB
WanVideo_comfy_fp8_scaledKijai
—
—
—
gemma-2-2b-itGoogle
~5.2 GB
~2.6 GB
~1.3 GB
Octen-Embedding-8BOcten
~15.1 GB
~7.6 GB
~3.8 GB
stanford-deidentifier-baseStanfordAIMI
—
—
—
Qwen2-VL-7B-InstructQwen
~16.6 GB
~8.3 GB
~4.2 GB
blip-image-captioning-largeSalesforce
~0.9 GB
~0.5 GB
~0.2 GB
mivolo_v2iitolstykh
~0.1 GB
~0.0 GB
~0.0 GB
minimax-h3-fused-turbo-int8-convrotMATLOWAI
—
—
—
Qwen2.5-VL-32B-InstructQwen
~66.9 GB
~33.5 GB
~16.7 GB
vae-text-encorder-for-flux-klein-9bComfy-Org
—
—
—
Minimax-h3_SingularityWarmBloodAban
—
—
—
Qwen3-Omni-30B-A3B-InstructQwen
~70.5 GB
~35.3 GB
~17.6 GB
NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4NVIDIA
~134.5 GB
~67.2 GB
~33.6 GB
snowflake-arctic-embed-l-v2.0Snowflake
~1.1 GB
~0.6 GB
~0.3 GB
wav2vec2-large-xlsr-53-arabicjonatasgrosman
—
—
—
mDeBERTa-v3-base-xnli-multilingual-nli-2mil7MoritzLaurer
~0.6 GB
~0.3 GB
~0.1 GB
Mistral-7B-v0.1Mistral AI
~14.5 GB
~7.2 GB
~3.6 GB
Inkling-Smallthinkingmachines
~531.9 GB
~266.0 GB
~133.0 GB
SmolLM3-3BHuggingFaceTB
~6.2 GB
~3.1 GB
~1.5 GB
GLM-5Z.ai
~1,507.7 GB
~753.9 GB
~376.9 GB
wav2vec2-large-xlsr-53-polishjonatasgrosman
—
—
—
gemma-4-31BGoogle
~65.4 GB
~32.7 GB
~16.3 GB
gte-smallthenlper
~0.1 GB
~0.0 GB
~0.0 GB
Mistral-Small-3.1-24B-Instruct-2503Mistral AI
~48.0 GB
~24.0 GB
~12.0 GB
bge-base-en-v1.5Xenova
—
—
—
chronos-bolt-baseautogluon
~0.4 GB
~0.2 GB
~0.1 GB
Kimi-K2.6Moonshot AI
~2,053.8 GB
~1,026.9 GB
~513.4 GB
segmentationpyannote
—
—
—
gender-classificationrizvandwiki
~0.2 GB
~0.1 GB
~0.0 GB
clap-htsat-unfusedlaion
—
—
—
answerai-colbert-small-v1answerdotai
~0.1 GB
~0.0 GB
~0.0 GB
jina-reranker-v3jinaai
~1.2 GB
~0.6 GB
~0.3 GB
faster-whisper-baseSystran
—
—
—
resnet50.a1_in1ktimm
~0.1 GB
~0.0 GB
~0.0 GB
resnet18.a1_in1ktimm
~0.0 GB
~0.0 GB
~0.0 GB
albert-base-v2albert
~0.0 GB
~0.0 GB
~0.0 GB
bloomz-560mBigScience
~1.1 GB
~0.6 GB
~0.3 GB
bge-large-zh-v1.5BAAI
—
—
—
MiniMax-M2.5MiniMax
~457.4 GB
~228.7 GB
~114.3 GB
ModernBERT-largeanswerdotai
~0.8 GB
~0.4 GB
~0.2 GB
DeepSeek-V4-Flash-DSparkDeepSeek
~330.5 GB
~165.3 GB
~82.6 GB
RMBG-2.0briaai
~0.4 GB
~0.2 GB
~0.1 GB
inclusively-reformulation-it5E-MIMIC
~1.6 GB
~0.8 GB
~0.4 GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8NVIDIA
~66.0 GB
~33.0 GB
~16.5 GB
Qwen3.6-35B-A3B-NVFP4unsloth
~49.3 GB
~24.6 GB
~12.3 GB
Qwen3-VLComfy-Org
—
—
—
FLUX.2-devBlack Forest Labs
~64.5 GB
~32.2 GB
~16.1 GB
chatglm2-6bZ.ai
—
—
—
Qwen2.5-7BQwen
~15.2 GB
~7.6 GB
~3.8 GB
Qwen3.5-122B-A10B-NVFP4NVIDIA
~129.2 GB
~64.6 GB
~32.3 GB
chronos-bolt-tinyautogluon
~0.0 GB
~0.0 GB
~0.0 GB
Ornith-1.5-35B-A3B-NVFP4ornith-ai
~39.1 GB
~19.5 GB
~9.8 GB
ltx-2Comfy-Org
—
—
—
distiluse-base-multilingual-cased-v2Sentence Transformers
~0.3 GB
~0.1 GB
~0.1 GB
longformer-base-4096AllenAI
—
—
—
Qwen3.5-397B-A17BQwen
~806.8 GB
~403.4 GB
~201.7 GB
ESMC-6Bbiohub
~12.7 GB
~6.3 GB
~3.2 GB
LTX2.3_comfyKijai
—
—
—
MiniCPM5-1Bopenbmb
~2.2 GB
~1.1 GB
~0.5 GB
siglip2-so400m-patch14-384Google
~2.3 GB
~1.1 GB
~0.6 GB
gemma-4-E4BGoogle
~16.0 GB
~8.0 GB
~4.0 GB
bert-large-uncasedgoogle-bert
~0.7 GB
~0.3 GB
~0.2 GB
dinov2-largeMeta
~0.6 GB
~0.3 GB
~0.1 GB
bert-base-multilingual-uncased-sentimentnlptown
~0.3 GB
~0.2 GB
~0.1 GB
embeddingpyannote
—
—
—
PP-DocLayoutV3_safetensorsPaddlePaddle
~0.1 GB
~0.0 GB
~0.0 GB
Qwen3.5-122B-A10BQwen
~250.2 GB
~125.1 GB
~62.5 GB
FLUX.1-Kontext-devBlack Forest Labs
~23.8 GB
~11.9 GB
~6.0 GB
emotion-english-distilroberta-basej-hartmann
—
—
—
Kronos-baseNeoQuasar
~0.2 GB
~0.1 GB
~0.1 GB
Qwen3-4B-Instruct-2507-FP8Qwen
~8.8 GB
~4.4 GB
~2.2 GB
Qwen3-Coder-30B-A3B-InstructQwen
~61.1 GB
~30.5 GB
~15.3 GB
twitter-xlm-roberta-base-sentimentcardiffnlp
—
—
—
blip2-opt-2.7bSalesforce
~7.5 GB
~3.7 GB
~1.9 GB
Cosmos-Reason2-2BNVIDIA
~4.9 GB
~2.4 GB
~1.2 GB
camembert-basealmanach
~0.2 GB
~0.1 GB
~0.1 GB
bert-tinyprajjwal1
—
—
—
DeepSeek-R1-Distill-Qwen-32BDeepSeek
~65.5 GB
~32.8 GB
~16.4 GB
Kimi-K2.5Moonshot AI
~2,053.8 GB
~1,026.9 GB
~513.4 GB
pythia-70m-dedupedEleutherAI
~0.2 GB
~0.1 GB
~0.1 GB
Qwen-Image-Edit-2509Qwen
~40.9 GB
~20.4 GB
~10.2 GB
opus-mt-nl-enHelsinki-NLP
—
—
—
distilbert-base-multilingual-cased-sentiments-studentlxyuan
~0.3 GB
~0.1 GB
~0.1 GB
Kimi-K2-InstructMoonshot AI
~2,052.8 GB
~1,026.4 GB
~513.2 GB
dragon-multiturn-query-encoderNVIDIA
—
—
—
roberta-base-squad2deepset
~0.2 GB
~0.1 GB
~0.1 GB
Qwen3.6-27B-NVFP4NVIDIA
~36.3 GB
~18.2 GB
~9.1 GB
deberta-v3-base-prompt-injection-v2protectai
~0.4 GB
~0.2 GB
~0.1 GB
Qwen3-4B-Thinking-2507Qwen
~8.0 GB
~4.0 GB
~2.0 GB
deberta-v3-largeMicrosoft
—
—
—
bigvgan_v2_22khz_80band_256xNVIDIA
—
—
—
distil-large-v3distil-whisper
~1.5 GB
~0.8 GB
~0.4 GB
privacy-filterOpenAI
~2.8 GB
~1.4 GB
~0.7 GB
Florence-2-largeMicrosoft
~1.6 GB
~0.8 GB
~0.4 GB
Kokoro-82M-v1.0-ONNXonnx-community
—
—
—
zerank-2-rerankerzeroentropy
~8.0 GB
~4.0 GB
~2.0 GB
chronos-bolt-baseamazon
~0.4 GB
~0.2 GB
~0.1 GB
DNABERT-2-117Mzhihan1996
—
—
—
wav2vec2-large-xlsr-53-dutchjonatasgrosman
—
—
—
Qwen3-235B-A22BQwen
~470.2 GB
~235.1 GB
~117.5 GB
UI-TARS-1.5-7BByteDance-Seed
~16.6 GB
~8.3 GB
~4.2 GB
gemma-3-12b-itGoogle
~24.4 GB
~12.2 GB
~6.1 GB
all-MiniLM-L6-v2-onnxQdrant
—
—
—
jina-embeddings-v5-omni-smalljinaai
~3.2 GB
~1.6 GB
~0.8 GB
tiny-gpt2sshleifer
—
—
—
jina-embeddings-v2-small-enjinaai
~0.1 GB
~0.0 GB
~0.0 GB
Qwen3.8-27B-NVFP4Inferact
~35.3 GB
~17.6 GB
~8.8 GB
CLIP-ViT-H-14-laion2B-s32B-b79Klaion
~2.0 GB
~1.0 GB
~0.5 GB
GLM-5.2-NVFP4NVIDIA
~762.0 GB
~381.0 GB
~190.5 GB
Qwen3-0.6B-BaseQwen
~1.2 GB
~0.6 GB
~0.3 GB
clipseg-rd64-refinedCIDAS
~0.3 GB
~0.1 GB
~0.1 GB
VieNeu-TTS-v3-Turbopnnbao-ump
~0.3 GB
~0.1 GB
~0.1 GB
LaBSESentence Transformers
~0.9 GB
~0.5 GB
~0.2 GB
grounding-dino-tinyIDEA-Research
~0.3 GB
~0.2 GB
~0.1 GB
Apertus-8B-Instruct-2509swiss-ai
~16.1 GB
~8.1 GB
~4.0 GB
Juggernaut-XL-v9RunDiffusion
—
—
—
e5-base-v2intfloat
~0.2 GB
~0.1 GB
~0.1 GB
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA
~63.2 GB
~31.6 GB
~15.8 GB
sd-turboStability AI
~1.7 GB
~0.9 GB
~0.4 GB
wav2vec2-indonesian-javanese-sundaneseindonesian-nlp
—
—
—
FLUX.2-klein-4BBlack Forest Labs
~7.8 GB
~3.9 GB
~1.9 GB
HunyuanVideo_1.5_repackagedComfy-Org
—
—
—
specter2_baseAllenAI
—
—
—
bigvgan_v2_44khz_128band_512xNVIDIA
—
—
—
gemma-4-12B-it-qat-w4a16-ctGoogle
~25.9 GB
~13.0 GB
~6.5 GB
gliner2-base-v1fastino
~0.4 GB
~0.2 GB
~0.1 GB
Apertus-v1.5-8Bswiss-ai
~17.8 GB
~8.9 GB
~4.5 GB
vit-base-nsfw-detectorAdamCodd
~0.2 GB
~0.1 GB
~0.0 GB
Phi-3.5-mini-instructMicrosoft
~7.6 GB
~3.8 GB
~1.9 GB
gemma-4-26B-A4B-it-FP8-dynamicRedHatAI
~53.1 GB
~26.5 GB
~13.3 GB
Qwen3.8-27B-NVFP4NVIDIA
~36.3 GB
~18.2 GB
~9.1 GB
multi-qa-MiniLM-L6-cos-v1Sentence Transformers
~0.1 GB
~0.0 GB
~0.0 GB
siglip2-base-patch16-naflexGoogle
~0.8 GB
~0.4 GB
~0.2 GB
stable-diffusion-safety-checkerCompVis
—
—
—
Ornith-1.5-9Bornith-ai
~19.3 GB
~9.7 GB
~4.8 GB
Hy3Tencent
~597.6 GB
~298.8 GB
~149.4 GB
bert-large-portuguese-casedneuralmind
—
—
—
GLM-5.1Z.ai
~1,507.7 GB
~753.9 GB
~376.9 GB
Pixal3DComfy-Org
—
—
—
UAE-Large-V1WhereIsAI
~0.7 GB
~0.3 GB
~0.2 GB
Phi-3-mini-4k-instructMicrosoft
~7.6 GB
~3.8 GB
~1.9 GB
Muse-Glimmer-30Bmeta-models
~59.5 GB
~29.8 GB
~14.9 GB
GigaAM-v3ai-sage
—
—
—
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4NVIDIA
~36.6 GB
~18.3 GB
~9.2 GB
Qwen3.8-27B-NVFP4-RTX5090gittensor-model-hub
~29.1 GB
~14.6 GB
~7.3 GB
JiRackUltra_1bCMSManhattan
~3.5 GB
~1.8 GB
~0.9 GB
OpenELM-1_1B-Instructapple
~2.2 GB
~1.1 GB
~0.5 GB
faster-whisper-mediumSystran
—
—
—
falcon-7bTechnology Innovation Institute
~14.4 GB
~7.2 GB
~3.6 GB
table-transformer-detectionMicrosoft
~0.1 GB
~0.0 GB
~0.0 GB
Mistral-Nemo-Instruct-2407Mistral AI
~24.5 GB
~12.2 GB
~6.1 GB
zetazed-industries
~15.2 GB
~7.6 GB
~3.8 GB
dreamshaper-7Lykon
~1.7 GB
~0.9 GB
~0.4 GB
MiniCPM5-2B-DSparkopenbmb
~0.7 GB
~0.3 GB
~0.2 GB
gpt-j-6bEleutherAI
—
—
—
e5-small-v2intfloat
~0.1 GB
~0.0 GB
~0.0 GB
snowflake-arctic-embed-lSnowflake
~0.7 GB
~0.3 GB
~0.2 GB
indic-conformer-600m-multilingualai4bharat
—
—
—
LTX-2Lightricks
~37.8 GB
~18.9 GB
~9.4 GB
flux1-schnellComfy-Org
—
—
—
opus-mt-fr-enHelsinki-NLP
~0.1 GB
~0.1 GB
~0.0 GB
deepseek-coder-7b-instruct-v1.5DeepSeek
~13.8 GB
~6.9 GB
~3.5 GB
Qwen3.6-35B-A3B-NVFP4-Fastunsloth
~43.6 GB
~21.8 GB
~10.9 GB
vit_small_patch14_dinov2.lvd142mtimm
~0.0 GB
~0.0 GB
~0.0 GB
GLM-5.2-FP8Z.ai
~1,506.7 GB
~753.3 GB
~376.7 GB
wikineural-multilingual-nerBabelscape
~0.3 GB
~0.2 GB
~0.1 GB
Kronos-smallNeoQuasar
~0.1 GB
~0.0 GB
~0.0 GB
dragon-multiturn-context-encoderNVIDIA
—
—
—
SeedVR2_comfyUInumz
—
—
—
distilbert-base-multilingual-caseddistilbert
~0.3 GB
~0.1 GB
~0.1 GB
gpt-neox-20bEleutherAI
~41.5 GB
~20.7 GB
~10.4 GB
resnet-50Microsoft
~0.1 GB
~0.0 GB
~0.0 GB
yolos-smallhustvl
~0.1 GB
~0.0 GB
~0.0 GB
GLM-4.5-AirZ.ai
~220.9 GB
~110.5 GB
~55.2 GB
Meta-Llama-3-8BMeta
~16.1 GB
~8.0 GB
~4.0 GB
Wan2.1DeepBeepMeep
—
—
—
Qwen2.5-VL-7B-Instruct-NVFP4NVIDIA
~10.1 GB
~5.0 GB
~2.5 GB
bert-large-cased-finetuned-conll03-englishdbmdz
~0.7 GB
~0.3 GB
~0.2 GB
llama-nemotron-rerank-1b-v2NVIDIA
~2.5 GB
~1.2 GB
~0.6 GB
deberta-v3-smallMicrosoft
—
—
—
tf_efficientnetv2_s.in21k_ft_in1ktimm
~0.0 GB
~0.0 GB
~0.0 GB
dinov3-vitb16-pretrain-lvd1689mMeta
~0.2 GB
~0.1 GB
~0.0 GB
bloom-560mBigScience
~1.1 GB
~0.6 GB
~0.3 GB
bge-small-en-v1.5-onnx-QQdrant
—
—
—
wd-swinv2-tagger-v3SmilingWolf
~0.2 GB
~0.1 GB
~0.1 GB
vae-text-encorder-for-flux-klein-4bComfy-Org
—
—
—
ko-sroberta-multitaskjhgan
~0.2 GB
~0.1 GB
~0.1 GB
Phi-4-mini-instructMicrosoft
~7.7 GB
~3.8 GB
~1.9 GB
wav2vec2-large-xlsr-koreankresnik
~0.6 GB
~0.3 GB
~0.2 GB
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA
~1,121.0 GB
~560.5 GB
~280.3 GB
CLIP-convnext_base_w-laion2B-s13B-b82K-augreglaion
—
—
—
chronos-t5-tinyamazon
~0.0 GB
~0.0 GB
~0.0 GB
LTX-2.3-fp8Lightricks
—
—
—
bge-micro-v2TaylorAI
~0.0 GB
~0.0 GB
~0.0 GB
unbiased-toxic-robertaunitary
—
—
—
flan-t5-smallGoogle
~0.1 GB
~0.1 GB
~0.0 GB
Hermes-3-Llama-3.1-8BNousResearch
~16.1 GB
~8.0 GB
~4.0 GB
RMBG-1.4briaai
~0.1 GB
~0.0 GB
~0.0 GB
ace_step_1.5_ComfyUI_filesComfy-Org
—
—
—
MiniCPM-V-4.6openbmb
~2.6 GB
~1.3 GB
~0.7 GB
blip-vqa-baseSalesforce
~0.8 GB
~0.4 GB
~0.2 GB
Realistic_Vision_V5.1_noVAESG161222
~1.7 GB
~0.9 GB
~0.4 GB
MiniCPM-o-2_6openbmb
~17.4 GB
~8.7 GB
~4.3 GB
SeedVR2Comfy-Org
—
—
—
whisper-tinyXenova
—
—
—
dpt-hybrid-midasIntel
—
—
—
layoutlm-document-qaimpira
~0.3 GB
~0.1 GB
~0.1 GB
MiniMax-M2MiniMax
~457.4 GB
~228.7 GB
~114.3 GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16NVIDIA
~66.0 GB
~33.0 GB
~16.5 GB
Mixtral-8x7B-Instruct-v0.1Mistral AI
~93.4 GB
~46.7 GB
~23.4 GB
nemotron-speech-streaming-en-0.6bNVIDIA
~1.2 GB
~0.6 GB
~0.3 GB
Giga-Embeddings-instructai-sage
~6.9 GB
~3.5 GB
~1.7 GB
SmolVLM-256M-InstructHuggingFaceTB
~0.5 GB
~0.3 GB
~0.1 GB
chandradatalab-to
~17.5 GB
~8.8 GB
~4.4 GB
LLaDA-8B-InstructGSAI-ML
~16.0 GB
~8.0 GB
~4.0 GB
DeepSeek-V3.1DeepSeek
~1,369.1 GB
~684.5 GB
~342.3 GB
stable-diffusion-3.5-fp8Comfy-Org
—
—
—
vitpose-plus-baseusyd-community
~0.2 GB
~0.1 GB
~0.1 GB
pythia-6.9bEleutherAI
~14.0 GB
~7.0 GB
~3.5 GB
gte-Qwen2-1.5B-instructAlibaba-NLP
~3.5 GB
~1.8 GB
~0.9 GB
gte-largethenlper
~0.7 GB
~0.3 GB
~0.2 GB
jina-embeddings-v2-base-enjinaai
~0.3 GB
~0.1 GB
~0.1 GB
RealVisXL_V5.0SG161222
~5.1 GB
~2.6 GB
~1.3 GB
Olmo-3-7B-InstructAllenAI
~14.6 GB
~7.3 GB
~3.6 GB
Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTPHauhauCS
—
—
—
MiniMax-Music-3Comfy-Org
—
—
—
gpt-neo-125mEleutherAI
~0.3 GB
~0.1 GB
~0.1 GB
Wan-Animate-2Comfy-Org
—
—
—
m2m100_418MMeta
—
—
—
InternVL2-1BOpenGVLab
~1.9 GB
~0.9 GB
~0.5 GB
granite-4.1-3bIBM
~6.8 GB
~3.4 GB
~1.7 GB
InternVL2-2BOpenGVLab
~4.4 GB
~2.2 GB
~1.1 GB
bge-base-zh-v1.5BAAI
—
—
—
unidepth-v2-vitl14lpiccinelli
~0.7 GB
~0.3 GB
~0.2 GB
BiomedNLP-BiomedBERT-base-uncased-abstract-fulltextMicrosoft
—
—
—
llava-v1.6-mistral-7b-hfllava-hf
~15.1 GB
~7.6 GB
~3.8 GB
wav2vec2-large-xlsr-53-thairesearch
—
—
—
yolo-world-mirrorBingsu
—
—
—
robertuito-sentiment-analysispysentimiento
~0.2 GB
~0.1 GB
~0.1 GB
animagine-xl-4.0cagliostrolab
~5.1 GB
~2.6 GB
~1.3 GB
nli-deberta-v3-basecross-encoder
~0.4 GB
~0.2 GB
~0.1 GB
CodeLlama-7b-hfcodellama
~13.5 GB
~6.7 GB
~3.4 GB
DeepSeek-R1-Distill-Qwen-14BDeepSeek
~29.5 GB
~14.8 GB
~7.4 GB
chronos-bolt-tinyamazon
~0.0 GB
~0.0 GB
~0.0 GB
MiniMax-H3DeepBeepMeep
—
—
—
NVIDIA-Nemotron-Nano-9B-v2NVIDIA
~17.8 GB
~8.9 GB
~4.4 GB
efficientnet_b3.ra2_in1ktimm
~0.0 GB
~0.0 GB
~0.0 GB
Qwen3.8-27B-INT4RedHatAI
~54.7 GB
~27.4 GB
~13.7 GB
mobilebert-uncasedGoogle
—
—
—
parakeet-tdt-0.6b-v2mlx-community
~1.2 GB
~0.6 GB
~0.3 GB
Ornith-1.5-35B-A3Bornith-ai
~71.9 GB
~36.0 GB
~18.0 GB
pythia-70mEleutherAI
~0.2 GB
~0.1 GB
~0.1 GB
xlm-roberta-base-language-detectionpapluca
~0.6 GB
~0.3 GB
~0.1 GB
DFN5B-CLIP-ViT-H-14-378apple
—
—
—
CLIP-ViT-B-16-laion2B-s34B-b88Klaion
—
—
—
wav2vec2-large-xlsr-53-hungarianjonatasgrosman
—
—
—
DeBERTa-v3-base-mnli-fever-anliMoritzLaurer
~0.4 GB
~0.2 GB
~0.1 GB
whisper-tiny.enXenova
—
—
—
granite-docling-258MIBM
~0.5 GB
~0.3 GB
~0.1 GB
mxbai-rerank-xsmall-v1mixedbread-ai
~0.1 GB
~0.1 GB
~0.0 GB
wav2vec2-large-xlsr-53-greekjonatasgrosman
—
—
—
distilbart-cnn-12-6sshleifer
—
—
—
macbert4csc-base-chineseshibing624
~0.2 GB
~0.1 GB
~0.1 GB
playground-v2.5-1024px-aestheticplaygroundai
~5.1 GB
~2.6 GB
~1.3 GB
splade-cocondenser-selfdistilnaver
—
—
—
seamless-m4t-v2-largeMeta
~4.6 GB
~2.3 GB
~1.1 GB
snac_24khzhubertsiuzdak
—
—
—
Qwen3.8-Flash-Next-NVFP4NVIDIA
~239.2 GB
~119.6 GB
~59.8 GB
SCAIL-2Comfy-Org
—
—
—
flan-t5-largeGoogle
~1.6 GB
~0.8 GB
~0.4 GB
medgemma-1.5-4b-itGoogle
~8.6 GB
~4.3 GB
~2.1 GB
all_miniLM_L6_v2_with_attentionsQdrant
—
—
—
cryptobertElKulako
~0.2 GB
~0.1 GB
~0.1 GB
ruri-v3-310mcl-nagoya
~0.6 GB
~0.3 GB
~0.2 GB
Olmo-3-7B-ThinkAllenAI
~14.6 GB
~7.3 GB
~3.6 GB
VGGT-1BMeta
~2.5 GB
~1.3 GB
~0.6 GB
DeepSeek-R1-0528DeepSeek
~1,369.1 GB
~684.5 GB
~342.3 GB
granite-timeseries-tspulse-r1IBM
~0.0 GB
~0.0 GB
~0.0 GB
rtdetr_r101vd_coco_o365PekingU
~0.1 GB
~0.1 GB
~0.0 GB
stsb-bert-tiny-safetensorssentence-transformers-testing
~0.0 GB
~0.0 GB
~0.0 GB
Sulphur-2-baseSulphurAI
—
—
—
Qwen3.8-27B-Uncensored-FP8orcarouter
~55.6 GB
~27.8 GB
~13.9 GB
Qianfan-OCRbaidu
~9.5 GB
~4.7 GB
~2.4 GB
MiMo-V2.6-Pro-RLXiaomi MiMo
~2,048.4 GB
~1,024.2 GB
~512.1 GB
K2-Horizon-375B-A23BInstitute of Foundation Models (IFM)
~758.3 GB
~379.2 GB
~189.6 GB
MiniMax-M3MiniMax
~854.1 GB
~427.0 GB
~213.5 GB
Mellum2.1-12B-A2.5B-ThinkingJetBrains
~24.3 GB
~12.2 GB
~6.1 GB
K2-Horizon-MoVA-36B-A4BInstitute of Foundation Models (IFM)
~74.9 GB
~37.4 GB
~18.7 GB
K2-Horizon-3.7BInstitute of Foundation Models (IFM)
~10.1 GB
~5.1 GB
~2.5 GB
clef-omniCloudflare
~70.5 GB
~35.3 GB
~17.6 GB
pplx-embed-v2-late-0.6bPerplexity
~1.2 GB
~0.6 GB
~0.3 GB
pplx-embed-v2-late-9bPerplexity
~16.8 GB
~8.4 GB
~4.2 GB
Qwen-Image-2.1-TurboQwen
~14.2 GB
~7.1 GB
~3.6 GB
Darwin-27B-ZTCFINAL-Bench
~51.2 GB
~25.6 GB
~12.8 GB
G9v3-3BAI9Stars
~6.0 GB
~3.0 GB
~1.5 GB
granite-4.2-3bIBM
~7.3 GB
~3.7 GB
~1.8 GB
Holo4-27BH Company
~54.7 GB
~27.4 GB
~13.7 GB
Granite 4.2 30BIBM
~58.5 GB
~29.3 GB
~14.6 GB
LightOnOCR-3-4BLightOn AI
~9.1 GB
~4.5 GB
~2.3 GB
Muse Spark Open 816B-A42BMeta
~1,632.0 GB
~816.0 GB
~408.0 GB
Muse Spark Open 816B-A42B NVFP4Meta
~1,632.0 GB
~816.0 GB
~408.0 GB
LFM2.5-24B-A2BLiquid AI
~47.9 GB
~24.0 GB
~12.0 GB
LFM2.5-24B-A2B BaseLiquid AI
~47.9 GB
~24.0 GB
~12.0 GB
Timestral-5MMistral AI
~0.0 GB
~0.0 GB
~0.0 GB
Timestral-28MMistral AI
~0.1 GB
~0.0 GB
~0.0 GB
Timestral-123MMistral AI
~0.2 GB
~0.1 GB
~0.1 GB
Timestral-209MMistral AI
~0.4 GB
~0.2 GB
~0.1 GB
Granite Switch 4.1 8BIBM
~17.6 GB
~8.8 GB
~4.4 GB
Granite Switch 4.1 30BIBM
~60.0 GB
~30.0 GB
~15.0 GB
HiRO-ACEv2Allen Institute for AI
—
—
—
DeepSeek V4.1 Flash 1017DeepSeek
~1,526.4 GB
~763.2 GB
~381.6 GB
Beam 1.0 BF16Reflection
~1,002.5 GB
~501.3 GB
~250.6 GB
Beam 1.0 FP8Reflection
~1,002.5 GB
~501.3 GB
~250.6 GB
Beam 1.0 NVFP4Reflection
~509.3 GB
~254.6 GB
~127.3 GB
Beam DFlash2 companion drafterReflection
~3.9 GB
~1.9 GB
~1.0 GB
Nemotron 3.5 Bolt IQ2 24GBNVIDIA
~49.1 GB
~24.6 GB
~12.3 GB
Nemotron 3.5 Bolt BF16NVIDIA
~149.8 GB
~74.9 GB
~37.4 GB
Nemotron 3.5 Super VL BF16NVIDIA
~248.9 GB
~124.5 GB
~62.2 GB
Nemotron 3.5 Super VL NVFP4NVIDIA
~131.5 GB
~65.8 GB
~32.9 GB
Nemotron Labs Dory 1.0 BF16NVIDIA
~8.0 GB
~4.0 GB
~2.0 GB
Nemotron Labs Dory 1.0 MXFP8NVIDIA
~8.0 GB
~4.0 GB
~2.0 GB
Nemotron Labs Dory 1.0 NVFP4NVIDIA
~4.7 GB
~2.3 GB
~1.2 GB
Nemotron Labs Dory 1.0 GGUF Q5_K_MNVIDIA
~8.0 GB
~4.0 GB
~2.0 GB
Nemotron 3.5 Embed 8B BF16NVIDIA
~16.8 GB
~8.4 GB
~4.2 GB
Nemotron 3.5 Rerank 8B BF16NVIDIA
~16.8 GB
~8.4 GB
~4.2 GB
Nemotron 3.5 Parse 631MNVIDIA
~1.3 GB
~0.6 GB
~0.3 GB
Ming 3.0 Audio FlashinclusionAI
~256.4 GB
~128.2 GB
~64.1 GB
Ming 3.0 Audio TinyinclusionAI
~17.7 GB
~8.9 GB
~4.4 GB
Ming 3.0 ASR TinyinclusionAI
~17.7 GB
~8.9 GB
~4.4 GB
Ming 3.0 TTS TinyinclusionAI
~18.0 GB
~9.0 GB
~4.5 GB
Hy-Memory 30B-A3BTencent
~60.0 GB
~30.0 GB
~15.0 GB
Qwen3.8 Flash Next DFlash 2 drafterInco AI
~1.2 GB
~0.6 GB
~0.3 GB
TranscribePsy 250M EUQVAC / Tether AI Research
~0.5 GB
~0.2 GB
~0.1 GB
GoTo AI Gemma 3 27B v3 InstructGoTo / AI Singapore
~54.0 GB
~27.0 GB
~13.5 GB
Step 5 Preview BF16stepfun-ai
~1,200.0 GB
~600.0 GB
~300.0 GB
Recursive Flint 40B-A2.5BRecursive
~79.6 GB
~39.8 GB
~19.9 GB
Ornith 1.5 122Bornith-ai
~250.2 GB
~125.1 GB
~62.5 GB
Granite Speech 5.0 2BIBM Granite
~4.6 GB
~2.3 GB
~1.2 GB
MiniMax M3.1 FlashMiniMax
~441.0 GB
~220.5 GB
~110.2 GB
Ling 3.1 FlashInclusionAI
~1,144.2 GB
~572.1 GB
~286.1 GB
Carbon-XHugging Face Biology Research
~29.6 GB
~14.8 GB
~7.4 GB
EmbeddingGemma 2Google DeepMind
~1.5 GB
~0.7 GB
~0.4 GB
AstaBrief 8BAi2
—
—
—
Atria DawnShanghai AI Laboratory
~1,506.7 GB
~753.3 GB
~376.7 GB
Nemotron 3.5 Bolt E4B BF16NVIDIA
~16.0 GB
~8.0 GB
~4.0 GB
Hy-NomasTencent Hunyuan
—
—
—
WeVisOne-VL 2BTencent WeChat Vision
~4.9 GB
~2.4 GB
~1.2 GB
WeVisOne-VL 4BTencent WeChat Vision
~9.7 GB
~4.8 GB
~2.4 GB
Mistral Large 4 (1T-A52B)Mistral AI
~2,100.0 GB
~1,050.0 GB
~525.0 GB
NVIDIA Nemotron 3.5 Transcribe 30B-A4BNVIDIA
~68.0 GB
~34.0 GB
~17.0 GB
Mage-VL-Cowork 4BMicrosoft
~9.5 GB
~4.7 GB
~2.4 GB
Nanbeige4.3-33BNanbeige
~66.2 GB
~33.1 GB
~16.6 GB
Surya OCR 2.5Datalab
~1.4 GB
~0.7 GB
~0.3 GB
SenseNova-Loop-9B-PreviewSenseNova
~19.3 GB
~9.7 GB
~4.8 GB
DeepSeek V4.1 Flash 1017 NVFP4NVIDIA
~1,329.8 GB
~664.9 GB
~332.4 GB
LFM3-1.7BLiquid AI
~3.5 GB
~1.7 GB
~0.9 GB
LFM3-Omni-2BLiquid AI
~4.3 GB
~2.2 GB
~1.1 GB
Xiaomi-OCR-0Xiaomi Research
~1.8 GB
~0.9 GB
~0.4 GB
IdolSperid Labs
—
—
—
Pika H3 FlexPika Labs
~66.2 GB
~33.1 GB
~16.6 GB
Qwen3.5-4B-3D-Coder (CCORE)CCORE
~9.1 GB
~4.5 GB
~2.3 GB
Kimi K3.1 ProMoonshot AI
—
—
—
Ripple-65B PreviewRicursive Intelligence
~129.6 GB
~64.8 GB
~32.4 GB
ERNIE 5.5 Flash BaseBaidu
~572.5 GB
~286.2 GB
~143.1 GB
MiniCPM-V 4.7 35B-A3BOpenBMB
~70.4 GB
~35.2 GB
~17.6 GB
MiniCPM-OCR 1.0OpenBMB
~2.6 GB
~1.3 GB
~0.7 GB
Phonon 31M EnglishGradium
~0.1 GB
~0.0 GB
~0.0 GB
Hydrogen-1.0Deep Principle
~1,506.7 GB
~753.3 GB
~376.7 GB
Laguna S 2.1Poolside
~235.1 GB
~117.6 GB
~58.8 GB
LongCat-2.5Meituan LongCat
~3,559.5 GB
~1,779.8 GB
~889.9 GB
MiniMax-H3-ImageMiniMax
—
—
—
LongCat-NextMeituan LongCat
~148.5 GB
~74.3 GB
~37.1 GB
ZONOS3-MiniZyphra
—
—
—
Bielik 11B v3.1 InstructSpeakLeash
~22.3 GB
~11.2 GB
~5.6 GB
Arete-27BNousResearch
~54.7 GB
~27.4 GB
~13.7 GB
Tencent Hy4 PreviewTencent
~1,559.9 GB
~780.0 GB
~390.0 GB
Inkling 2 SmallThinking Machines Lab
~766.1 GB
~383.1 GB
~191.5 GB
SOV-Transcribe-1Salesforce Sovereign Intelligence
~53.3 GB
~26.6 GB
~13.3 GB
Praxis-1 BaseRunway
~54.4 GB
~27.2 GB
~13.6 GB
PAN 2Institute of Foundation Models (MBZUAI)
~58.4 GB
~29.2 GB
~14.6 GB
Nex-N2.6Nex-AGI
~642.6 GB
~321.3 GB
~160.7 GB
Granite 4.1 8B LLMON PreviewIBM Granite
~17.6 GB
~8.8 GB
~4.4 GB
Raon-1 nanoKRAFTON AI
~7.1 GB
~3.5 GB
~1.8 GB
BotPsy-0.8BQVAC / Tether AI Research
~1.7 GB
~0.8 GB
~0.4 GB
Step 5 PreviewStepFun AI
~1,208.7 GB
~604.3 GB
~302.2 GB
Cosmos3-Nano-Transfer-AutoNVIDIA
~30.3 GB
~15.2 GB
~7.6 GB
Cosmos3-Nano-Sim-AutoNVIDIA
~30.3 GB
~15.2 GB
~7.6 GB
Cosmos3-Nano-Sim-TransferNVIDIA
~30.3 GB
~15.2 GB
~7.6 GB
Cosmos3-Nano-Sim-BimanualNVIDIA
~30.4 GB
~15.2 GB
~7.6 GB
PLaMo 3 Translate 0.8BPreferred Networks
~1.8 GB
~0.9 GB
~0.5 GB
PLaMo 3 Translate 2BPreferred Networks
~5.8 GB
~2.9 GB
~1.4 GB
PLaMo 3 Translate 8BPreferred Networks
~17.1 GB
~8.5 GB
~4.3 GB
PLaMo 3 Translate 31BPreferred Networks
~63.5 GB
~31.8 GB
~15.9 GB
Lara 4 Mini BaseTranslated
~14.6 GB
~7.3 GB
~3.6 GB
Haru-4BHigurashi AI
~10.5 GB
~5.3 GB
~2.6 GB
LongCat-Video-Avatar 1.6Meituan LongCat
—
—
—
Tess-4.5-594B-A17BContinuity Research
~766.1 GB
~383.1 GB
~191.5 GB
Olala v1.0 Mini 7A1BOVHcloud / OVHai LLM
~13.6 GB
~6.8 GB
~3.4 GB
Tencent Hy4 FlashTencent Hy Team
~440.0 GB
~220.0 GB
~110.0 GB
Sage S2.1 FlashShanghai AI Laboratory / InternLM
~642.0 GB
~321.0 GB
~160.5 GB
DaisyRose-27BRadixArk
~55.6 GB
~27.8 GB
~13.9 GB
Aion 1.0 Instruct 2.3BMicrosoft Windows Applied Sciences Group
~4.6 GB
~2.3 GB
~1.1 GB
Rumble-2-FlashReson8
~1.0 GB
~0.5 GB
~0.2 GB

Scope: Numerical estimates derive from available parameter counts; they do not verify released quantization variants or that a model will run within the selected capacity. See each model profile for exact source evidence.

HOW TO INTERPRET THESE NUMBERS

Weights are only the starting point.

01

Weight storage

These figures estimate parameter-storage bytes for a requested precision in decimal gigabytes. They are not measurements of an inference server.

02

Runtime memory

Inference also needs KV cache, activations, runtime allocations and sometimes multiple devices. Context length, batch size and framework matter.

03

Actual performance

Memory estimates do not predict latency, throughput, task quality or deployment cost. Those require reproducible execution measurements.