HARDWARE EXPLORER · WEIGHT-ONLY MEMORY
How much memory do the weights need?
Filter by a hardware budget and precision. Estimates cover model weights only — not KV cache, activations, runtime overhead or sharding.
Evidence statusSource-first verified
Field evidence checked2026-10-02
Full field verification2026-10-02
561 models match
Model
BF16 / FP16
FP8 / INT8
INT4
mobilenetv3_small_100.lamb_in1ktimm · 0.00255497B
0.0 GB
0.0 GB
0.0 GB
tiny-Qwen2ForCausalLM-2.5trl-internal-testing · 0.00243502B
0.0 GB
0.0 GB
0.0 GB
Ornith-1.0-35Bornith-ai · 0.000664944B
0.0 GB
0.0 GB
0.0 GB
Kronos-Tokenizer-baseNeoQuasar · 0.00395826B
0.0 GB
0.0 GB
0.0 GB
Ornith-1.0-9Bornith-ai · 0.00146968B
0.0 GB
0.0 GB
0.0 GB
chronos-bolt-tinyautogluon · 0.00865267B
0.0 GB
0.0 GB
0.0 GB
chronos-t5-tinyamazon · 0.0083945B
0.0 GB
0.0 GB
0.0 GB
chronos-bolt-tinyamazon · 0.00865267B
0.0 GB
0.0 GB
0.0 GB
stsb-bert-tiny-safetensorssentence-transformers-testing · 0.00438592B
0.0 GB
0.0 GB
0.0 GB
Llama-Prompt-Guard-2-22MMeta · 22M
0.0 GB
0.0 GB
0.0 GB
all-MiniLM-L6-v2Sentence Transformers · 0.0227137B
0.1 GB
0.0 GB
0.0 GB
ms-marco-MiniLM-L6-v2cross-encoder · 0.0227141B
0.1 GB
0.0 GB
0.0 GB
bge-small-zh-v1.5BAAI · 0.0239544B
0.1 GB
0.0 GB
0.0 GB
ms-marco-MiniLM-L4-v2cross-encoder · 0.0191652B
0.0 GB
0.0 GB
0.0 GB
dinov2-smallMeta · 0.0220566B
0.0 GB
0.0 GB
0.0 GB
chronos-2-smallautogluon · 0.0279346B
0.1 GB
0.0 GB
0.0 GB
Depth-Anything-V2-Small-hfdepth-anything · 0.0247851B
0.1 GB
0.0 GB
0.0 GB
paraphrase-MiniLM-L6-v2Sentence Transformers · 0.0227137B
0.1 GB
0.0 GB
0.0 GB
table-transformer-structure-recognitionMicrosoft · 0.0288478B
0.1 GB
0.0 GB
0.0 GB
mivolo_v2iitolstykh · 0.0287618B
0.1 GB
0.0 GB
0.0 GB
resnet50.a1_in1ktimm · 0.0256102B
0.1 GB
0.0 GB
0.0 GB
albert-base-v2albert · 0.0118423B
0.0 GB
0.0 GB
0.0 GB
resnet18.a1_in1ktimm · 0.0116991B
0.0 GB
0.0 GB
0.0 GB
multi-qa-MiniLM-L6-cos-v1Sentence Transformers · 0.0227137B
0.1 GB
0.0 GB
0.0 GB
resnet-50Microsoft · 0.0256102B
0.1 GB
0.0 GB
0.0 GB
table-transformer-detectionMicrosoft · 0.0288186B
0.1 GB
0.0 GB
0.0 GB
tf_efficientnetv2_s.in21k_ft_in1ktimm · 0.0216124B
0.0 GB
0.0 GB
0.0 GB
Kronos-smallNeoQuasar · 0.0247417B
0.1 GB
0.0 GB
0.0 GB
bge-micro-v2TaylorAI · 0.0173898B
0.0 GB
0.0 GB
0.0 GB
vit_small_patch14_dinov2.lvd142mtimm · 0.0220562B
0.0 GB
0.0 GB
0.0 GB
efficientnet_b3.ra2_in1ktimm · 0.0123205B
0.0 GB
0.0 GB
0.0 GB
dinov3-vits16-pretrain-lvd1689mMeta · 0.0215965B
0.0 GB
0.0 GB
0.0 GB
bge-small-en-v1.5BAAI · 0.0333605B
0.1 GB
0.0 GB
0.0 GB
all-MiniLM-L12-v2Sentence Transformers · 0.0333605B
0.1 GB
0.0 GB
0.0 GB
chronos-bolt-smallamazon · 0.047718B
0.1 GB
0.1 GB
0.0 GB
granite-embedding-small-english-r2IBM · 0.0476625B
0.1 GB
0.1 GB
0.0 GB
chronos-bolt-smallautogluon · 0.047718B
0.1 GB
0.1 GB
0.0 GB
whisper-tinyOpenAI · 0.0377606B
0.1 GB
0.0 GB
0.0 GB
ms-marco-MiniLM-L12-v2cross-encoder · 0.0333609B
0.1 GB
0.0 GB
0.0 GB
docling-layout-herondocling-project · 0.04289B
0.1 GB
0.0 GB
0.0 GB
chronos-t5-smallamazon · 0.0461542B
0.1 GB
0.1 GB
0.0 GB
gte-smallthenlper · 0.0333605B
0.1 GB
0.0 GB
0.0 GB
answerai-colbert-small-v1answerdotai · 0.0333969B
0.1 GB
0.0 GB
0.0 GB
PP-DocLayoutV3_safetensorsPaddlePaddle · 0.033289B
0.1 GB
0.0 GB
0.0 GB
jina-embeddings-v2-small-enjinaai · 0.0326907B
0.1 GB
0.0 GB
0.0 GB
e5-small-v2intfloat · 0.0333605B
0.1 GB
0.0 GB
0.0 GB
yolos-smallhustvl · 0.0306848B
0.1 GB
0.0 GB
0.0 GB
RMBG-1.4briaai · 0.0440756B
0.1 GB
0.0 GB
0.0 GB
detr-resnet-50Meta · 0.041631B
0.1 GB
0.0 GB
0.0 GB
t5-smallgoogle-t5 · 0.0605069B
0.1 GB
0.1 GB
0.0 GB
distilbert-base-uncaseddistilbert · 0.0669855B
0.1 GB
0.1 GB
0.0 GB
distilbert-base-uncased-finetuned-sst-2-englishdistilbert · 0.066955B
0.1 GB
0.1 GB
0.0 GB
Llama-Prompt-Guard-2-86MMeta · 86M
0.2 GB
0.1 GB
0.0 GB
vit-base-patch16-224Google · 0.0865677B
0.2 GB
0.1 GB
0.0 GB
nsfw_image_detectionFalconsai · 0.0858002B
0.2 GB
0.1 GB
0.0 GB
distilgpt2distilbert · 0.088204B
0.2 GB
0.1 GB
0.0 GB
dinov2-baseMeta · 0.0865805B
0.2 GB
0.1 GB
0.0 GB
vit-base-patch16-224-in21kGoogle · 0.0863892B
0.2 GB
0.1 GB
0.0 GB
whisper-baseOpenAI · 0.0725939B
0.1 GB
0.1 GB
0.0 GB
all-distilroberta-v1Sentence Transformers · 0.0821189B
0.2 GB
0.1 GB
0.0 GB
distilroberta-basedistilbert · 0.0827608B
0.2 GB
0.1 GB
0.0 GB
ast-finetuned-audioset-10-10-0.4593MIT · 0.0865941B
0.2 GB
0.1 GB
0.0 GB
gender-classificationrizvandwiki · 0.0858002B
0.2 GB
0.1 GB
0.0 GB
vit-base-nsfw-detectorAdamCodd · 0.086092B
0.2 GB
0.1 GB
0.0 GB
opus-mt-fr-enHelsinki-NLP · 0.0751935B
0.1 GB
0.1 GB
0.0 GB
dinov3-vitb16-pretrain-lvd1689mMeta · 0.0856604B
0.2 GB
0.1 GB
0.0 GB
flan-t5-smallGoogle · 0.0769612B
0.1 GB
0.1 GB
0.0 GB
mxbai-rerank-xsmall-v1mixedbread-ai · 0.0708303B
0.1 GB
0.1 GB
0.0 GB
rtdetr_r101vd_coco_o365PekingU · 0.0767987B
0.1 GB
0.1 GB
0.0 GB
all-mpnet-base-v2Sentence Transformers · 0.109487B
0.2 GB
0.1 GB
0.1 GB
bge-base-en-v1.5BAAI · 0.109483B
0.2 GB
0.1 GB
0.1 GB
bert-base-casedgoogle-bert · 0.108933B
0.2 GB
0.1 GB
0.1 GB
colbertv2.0colbert-ir · 0.109581B
0.2 GB
0.1 GB
0.1 GB
bert-base-NERdslim · 0.108317B
0.2 GB
0.1 GB
0.1 GB
wav2vec2-base-960hMeta · 0.0943956B
0.2 GB
0.1 GB
0.1 GB
bert-base-chinesegoogle-bert · 0.102882B
0.2 GB
0.1 GB
0.1 GB
multi-qa-mpnet-base-dot-v1Sentence Transformers · 0.109487B
0.2 GB
0.1 GB
0.1 GB
text2vec-base-chineseshibing624 · 0.102268B
0.2 GB
0.1 GB
0.1 GB
bge-base-en-v1.5-course-recommender-v5datasocietyco · 0.109482B
0.2 GB
0.1 GB
0.1 GB
bge-base-enBAAI · 0.109483B
0.2 GB
0.1 GB
0.1 GB
paraphrase-mpnet-base-v2Sentence Transformers · 0.109487B
0.2 GB
0.1 GB
0.1 GB
pubmedbert-base-embeddingsNeuML · 0.109482B
0.2 GB
0.1 GB
0.1 GB
SapBERT-from-PubMedBERT-fulltextcambridgeltl · 0.109483B
0.2 GB
0.1 GB
0.1 GB
Kronos-baseNeoQuasar · 0.102311B
0.2 GB
0.1 GB
0.1 GB
pythia-70m-dedupedEleutherAI · 0.0955925B
0.2 GB
0.1 GB
0.1 GB
e5-base-v2intfloat · 0.109483B
0.2 GB
0.1 GB
0.1 GB
wd-swinv2-tagger-v3SmilingWolf · 0.0980263B
0.2 GB
0.1 GB
0.1 GB
robertuito-sentiment-analysispysentimiento · 0.108791B
0.2 GB
0.1 GB
0.1 GB
pythia-70mEleutherAI · 0.0955925B
0.2 GB
0.1 GB
0.1 GB
macbert4csc-base-chineseshibing624 · 0.102291B
0.2 GB
0.1 GB
0.1 GB
paraphrase-multilingual-MiniLM-L12-v2Sentence Transformers · 0.117654B
0.2 GB
0.1 GB
0.1 GB
bert-base-uncasedgoogle-bert · 0.110106B
0.2 GB
0.1 GB
0.1 GB
chronos-2amazon · 0.119478B
0.2 GB
0.1 GB
0.1 GB
multilingual-e5-smallintfloat · 0.117654B
0.2 GB
0.1 GB
0.1 GB
roberta-baseFacebookAI · 0.124698B
0.2 GB
0.1 GB
0.1 GB
chronos-2autogluon · 0.119478B
0.2 GB
0.1 GB
0.1 GB
roberta-base-go_emotionsSamLowe · 0.124668B
0.2 GB
0.1 GB
0.1 GB
mmarco-mMiniLMv2-L12-H384-v1cross-encoder · 0.117642B
0.2 GB
0.1 GB
0.1 GB
layoutlmv3-baseMicrosoft · 0.125327B
0.2 GB
0.1 GB
0.1 GB
indonesian-roberta-base-posp-taggerw11wo · 0.124075B
0.2 GB
0.1 GB
0.1 GB
camembert-basealmanach · 0.111246B
0.2 GB
0.1 GB
0.1 GB
roberta-base-squad2deepset · 0.124057B
0.2 GB
0.1 GB
0.1 GB
ko-sroberta-multitaskjhgan · 0.110619B
0.2 GB
0.1 GB
0.1 GB
layoutlm-document-qaimpira · 0.127793B
0.3 GB
0.1 GB
0.1 GB
vitpose-plus-baseusyd-community · 0.125396B
0.2 GB
0.1 GB
0.1 GB
cryptobertElKulako · 0.124648B
0.2 GB
0.1 GB
0.1 GB
gpt2openai-community · 0.137023B
0.3 GB
0.1 GB
0.1 GB
nomic-embed-text-v1.5nomic-ai · 0.136732B
0.3 GB
0.1 GB
0.1 GB
ModernBERT-baseanswerdotai · 0.149655B
0.3 GB
0.1 GB
0.1 GB
nomic-embed-text-v1nomic-ai · 0.136732B
0.3 GB
0.1 GB
0.1 GB
SmolLM2-135M-InstructHuggingFaceTB · 0.134515B
0.3 GB
0.1 GB
0.1 GB
SmolLM2-135MHuggingFaceTB · 0.134515B
0.3 GB
0.1 GB
0.1 GB
gte-reranker-modernbert-baseAlibaba-NLP · 0.149606B
0.3 GB
0.1 GB
0.1 GB
turn-detectorlivekit · 0.134516B
0.3 GB
0.1 GB
0.1 GB
distiluse-base-multilingual-cased-v1Sentence Transformers · 0.134734B
0.3 GB
0.1 GB
0.1 GB
distiluse-base-multilingual-cased-v2Sentence Transformers · 0.134734B
0.3 GB
0.1 GB
0.1 GB
distilbert-base-multilingual-cased-sentiments-studentlxyuan · 0.135327B
0.3 GB
0.1 GB
0.1 GB
VieNeu-TTS-v3-Turbopnnbao-ump · 0.130908B
0.3 GB
0.1 GB
0.1 GB
distilbert-base-multilingual-caseddistilbert · 0.135446B
0.3 GB
0.1 GB
0.1 GB
jina-embeddings-v2-base-enjinaai · 0.137368B
0.3 GB
0.1 GB
0.1 GB
clap-htsat-fusedlaion · 0.153558B
0.3 GB
0.1 GB
0.1 GB
CLIP-ViT-B-32-laion2B-s34B-b79Klaion · 0.151277B
0.3 GB
0.1 GB
0.1 GB
bert-base-multilingual-uncasedgoogle-bert · 0.168056B
0.3 GB
0.2 GB
0.1 GB
fashion-clippatrickjohncyh · 0.151277B
0.3 GB
0.1 GB
0.1 GB
owlv2-base-patch16-ensembleGoogle · 0.154967B
0.3 GB
0.1 GB
0.1 GB
bert-base-multilingual-uncased-sentimentnlptown · 0.16736B
0.3 GB
0.2 GB
0.1 GB
clipseg-rd64-refinedCIDAS · 0.150748B
0.3 GB
0.1 GB
0.1 GB
gpt-neo-125mEleutherAI · 0.150364B
0.3 GB
0.1 GB
0.1 GB
wav2vec2-large-robust-12-ft-emotion-msp-dimaudeering · 0.165337B
0.3 GB
0.2 GB
0.1 GB
bert-base-multilingual-casedgoogle-bert · 0.178567B
0.4 GB
0.2 GB
0.1 GB
deberta-v3-base-prompt-injection-v2protectai · 0.184424B
0.4 GB
0.2 GB
0.1 GB
grounding-dino-tinyIDEA-Research · 0.172278B
0.3 GB
0.2 GB
0.1 GB
wikineural-multilingual-nerBabelscape · 0.17727B
0.3 GB
0.2 GB
0.1 GB
nli-deberta-v3-basecross-encoder · 0.184425B
0.4 GB
0.2 GB
0.1 GB
DeBERTa-v3-base-mnli-fever-anliMoritzLaurer · 0.184425B
0.4 GB
0.2 GB
0.1 GB
siglip-base-patch16-224Google · 0.203156B
0.4 GB
0.2 GB
0.1 GB
chronos-bolt-baseautogluon · 0.205293B
0.4 GB
0.2 GB
0.1 GB
chronos-bolt-baseamazon · 0.205293B
0.4 GB
0.2 GB
0.1 GB
gliner2-base-v1fastino · 0.208477B
0.4 GB
0.2 GB
0.1 GB
t5-basegoogle-t5 · 0.222904B
0.5 GB
0.2 GB
0.1 GB
pythia-160mEleutherAI · 0.212655B
0.4 GB
0.2 GB
0.1 GB
BiRefNetZhengPeng7 · 0.2207B
0.4 GB
0.2 GB
0.1 GB
RMBG-2.0briaai · 0.2207B
0.4 GB
0.2 GB
0.1 GB
whisper-smallOpenAI · 0.241735B
0.5 GB
0.2 GB
0.1 GB
Florence-2-baseMicrosoft · 0.231568B
0.5 GB
0.2 GB
0.1 GB
flan-t5-baseGoogle · 0.247578B
0.5 GB
0.2 GB
0.1 GB
timesfm-2.5-200m-pytorchGoogle · 0.231289B
0.5 GB
0.2 GB
0.1 GB
grounding-dino-baseIDEA-Research · 0.232811B
0.5 GB
0.2 GB
0.1 GB
SmolVLM-256M-InstructHuggingFaceTB · 0.256485B
0.5 GB
0.3 GB
0.1 GB
xlm-roberta-baseFacebookAI · 0.278886B
0.6 GB
0.3 GB
0.1 GB
paraphrase-multilingual-mpnet-base-v2Sentence Transformers · 0.278044B
0.6 GB
0.3 GB
0.1 GB
multilingual-e5-baseintfloat · 0.278044B
0.6 GB
0.3 GB
0.1 GB
bge-reranker-baseBAAI · 0.278045B
0.6 GB
0.3 GB
0.1 GB
jina-reranker-v2-base-multilingualjinaai · 0.278438B
0.6 GB
0.3 GB
0.1 GB
mDeBERTa-v3-base-xnli-multilingual-nli-2mil7MoritzLaurer · 0.278812B
0.6 GB
0.3 GB
0.1 GB
xlm-roberta-base-language-detectionpapluca · 0.27806B
0.6 GB
0.3 GB
0.1 GB
Prompt-Guard-86MMeta · 0.3B
0.6 GB
0.3 GB
0.1 GB
embeddinggemma-300mGoogle · 0.302863B
0.6 GB
0.3 GB
0.1 GB
gte-multilingual-baseAlibaba-NLP · 0.305369B
0.6 GB
0.3 GB
0.1 GB
dinov3-vitl16-pretrain-lvd1689mMeta · 0.30313B
0.6 GB
0.3 GB
0.1 GB
mms-300m-1130-forced-alignerMahmoudAshraf · 0.315469B
0.6 GB
0.3 GB
0.2 GB
wav2vec2-large-robust-24-ft-age-genderaudeering · 0.317542B
0.6 GB
0.3 GB
0.2 GB
MiniCPM5-2B-DSparkopenbmb · 0.323776B
0.7 GB
0.3 GB
0.2 GB
wav2vec2-large-xlsr-koreankresnik · 0.316674B
0.6 GB
0.3 GB
0.2 GB
ruri-v3-310mcl-nagoya · 0.314612B
0.6 GB
0.3 GB
0.2 GB
bge-large-en-v1.5BAAI · 0.335142B
0.7 GB
0.3 GB
0.2 GB
mxbai-embed-large-v1mixedbread-ai · 0.335142B
0.7 GB
0.3 GB
0.2 GB
timesfm-3.0-pytorchGoogle · 0.330711B
0.7 GB
0.3 GB
0.2 GB
e5-large-v2intfloat · 0.335142B
0.7 GB
0.3 GB
0.2 GB
bert-large-uncasedgoogle-bert · 0.336226B
0.7 GB
0.3 GB
0.2 GB
UAE-Large-V1WhereIsAI · 0.335142B
0.7 GB
0.3 GB
0.2 GB
bert-large-cased-finetuned-conll03-englishdbmdz · 0.333588B
0.7 GB
0.3 GB
0.2 GB
snowflake-arctic-embed-lSnowflake · 0.334092B
0.7 GB
0.3 GB
0.2 GB
gte-largethenlper · 0.335142B
0.7 GB
0.3 GB
0.2 GB
roberta-largeFacebookAI · 0.355413B
0.7 GB
0.4 GB
0.2 GB
unidepth-v2-vitl14lpiccinelli · 0.353831B
0.7 GB
0.3 GB
0.2 GB
all-roberta-large-v1Sentence Transformers · 0.35536B
0.7 GB
0.4 GB
0.2 GB
siglip2-base-patch16-256Google · 0.375234B
0.8 GB
0.4 GB
0.2 GB
siglip2-base-patch16-224Google · 0.375188B
0.8 GB
0.4 GB
0.2 GB
siglip2-base-patch16-naflexGoogle · 0.375234B
0.8 GB
0.4 GB
0.2 GB
blip-vqa-baseSalesforce · 0.384674B
0.8 GB
0.4 GB
0.2 GB
bart-large-mnliMeta · 0.407344B
0.8 GB
0.4 GB
0.2 GB
bart-large-cnnMeta · 0.40629B
0.8 GB
0.4 GB
0.2 GB
ModernBERT-largeanswerdotai · 0.395882B
0.8 GB
0.4 GB
0.2 GB
clip-vit-large-patch14OpenAI · 0.427617B
0.9 GB
0.4 GB
0.2 GB
CLIP-ViT-L-14-laion2B-s32B-b82Klaion · 0.427617B
0.9 GB
0.4 GB
0.2 GB
gte-large-en-v1.5Alibaba-NLP · 0.434139B
0.9 GB
0.4 GB
0.2 GB
blip-image-captioning-largeSalesforce · 0.469733B
0.9 GB
0.5 GB
0.2 GB
nomic-embed-text-v2-moenomic-ai · 0.475293B
0.9 GB
0.5 GB
0.2 GB
LaBSESentence Transformers · 0.470927B
0.9 GB
0.5 GB
0.2 GB
Qwen2.5-0.5B-InstructQwen · 0.494033B
1.0 GB
0.5 GB
0.2 GB
Qwen2.5-0.5BQwen · 0.494033B
1.0 GB
0.5 GB
0.2 GB
SmolVLM2-500M-Video-InstructHuggingFaceTB · 0.507482B
1.0 GB
0.5 GB
0.2 GB
bge-reranker-v2-m3BAAI · 0.567756B
1.1 GB
0.6 GB
0.3 GB
multilingual-e5-largeintfloat · 0.559891B
1.1 GB
0.6 GB
0.3 GB
xlm-roberta-largeFacebookAI · 0.561192B
1.1 GB
0.6 GB
0.3 GB
bge-reranker-largeBAAI · 0.559892B
1.1 GB
0.6 GB
0.3 GB
xlm-roberta-large-xnlijoeddav · 0.560944B
1.1 GB
0.6 GB
0.3 GB
multilingual-e5-large-instructintfloat · 0.55989B
1.1 GB
0.6 GB
0.3 GB
snowflake-arctic-embed-l-v2.0Snowflake · 0.567755B
1.1 GB
0.6 GB
0.3 GB
bloomz-560mBigScience · 0.559215B
1.1 GB
0.6 GB
0.3 GB
bloom-560mBigScience · 0.559215B
1.1 GB
0.6 GB
0.3 GB
jina-embeddings-v3jinaai · 0.57231B
1.1 GB
0.6 GB
0.3 GB
w2v-bert-2.0Meta · 0.580493B
1.2 GB
0.6 GB
0.3 GB
Qwen3Guard-Stream-0.6BQwen · 0.6B
1.2 GB
0.6 GB
0.3 GB
Qwen3-Embedding-0.6BQwen · 0.6B
1.2 GB
0.6 GB
0.3 GB
Qwen3-Reranker-0.6BQwen · 0.6B
1.2 GB
0.6 GB
0.3 GB
jina-reranker-v3jinaai · 0.596836B
1.2 GB
0.6 GB
0.3 GB
Qwen3-0.6B-BaseQwen · 0.59605B
1.2 GB
0.6 GB
0.3 GB
OmniVoicek2-fsa · 0.612577B
1.2 GB
0.6 GB
0.3 GB
parakeet-tdt-0.6b-v3mlx-community · 0.627052B
1.2 GB
0.6 GB
0.3 GB
parakeet-tdt-0.6b-v3NVIDIA · 0.627057B
1.2 GB
0.6 GB
0.3 GB
nemotron-speech-streaming-en-0.6bNVIDIA · 0.618085B
1.2 GB
0.6 GB
0.3 GB
parakeet-tdt-0.6b-v2mlx-community · 0.61787B
1.2 GB
0.6 GB
0.3 GB
nemotron-3.5-asr-streaming-0.6bNVIDIA · 0.637997B
1.3 GB
0.6 GB
0.3 GB
esm2_t33_650M_UR50DMeta · 0.652359B
1.3 GB
0.7 GB
0.3 GB
surya-ocr-2datalab-to · 0.686154B
1.4 GB
0.7 GB
0.3 GB
GOT-OCR2_0stepfun-ai · 0.716033B
1.4 GB
0.7 GB
0.4 GB
Qwen3-0.6BQwen · 0.751632B
1.5 GB
0.8 GB
0.4 GB
distil-large-v3distil-whisper · 0.756406B
1.5 GB
0.8 GB
0.4 GB
inclusively-reformulation-it5E-MIMIC · 0.783099B
1.6 GB
0.8 GB
0.4 GB
Florence-2-largeMicrosoft · 0.776721B
1.6 GB
0.8 GB
0.4 GB
flan-t5-largeGoogle · 0.78315B
1.6 GB
0.8 GB
0.4 GB
Qwen3-ASR-0.6B-hfQwen · 0.8B
1.6 GB
0.8 GB
0.4 GB
whisper-large-v3-turboOpenAI · 0.808878B
1.6 GB
0.8 GB
0.4 GB
gpt2-largeopenai-community · 0.811779B
1.6 GB
0.8 GB
0.4 GB
sam3Meta · 0.859922B
1.7 GB
0.9 GB
0.4 GB
stable-diffusion-v1-5stable-diffusion-v1-5 · 0.859521B
1.7 GB
0.9 GB
0.4 GB
stable-diffusion-v1-4CompVis · 0.859521B
1.7 GB
0.9 GB
0.4 GB
sd-turboStability AI · 0.865911B
1.7 GB
0.9 GB
0.4 GB
dreamshaper-7Lykon · 0.859521B
1.7 GB
0.9 GB
0.4 GB
Realistic_Vision_V5.1_noVAESG161222 · 0.859521B
1.7 GB
0.9 GB
0.4 GB
Qwen3.5-0.8BQwen · 0.873439B
1.8 GB
0.9 GB
0.4 GB
siglip-so400m-patch14-384Google · 0.87796B
1.8 GB
0.9 GB
0.4 GB
Qwen3-ForcedAligner-0.6B-hfQwen · 0.9B
1.8 GB
0.9 GB
0.5 GB
Qwen3.5-0.8B-BaseQwen · 0.9B
1.8 GB
0.9 GB
0.5 GB
Qwen3-TTS-12Hz-0.6B-CustomVoiceQwen · 0.905789B
1.8 GB
0.9 GB
0.5 GB
InternVL2-1BOpenGVLab · 0.938159B
1.9 GB
0.9 GB
0.5 GB
CLIP-ViT-H-14-laion2B-s32B-b79Klaion · 0.98611B
2.0 GB
1.0 GB
0.5 GB
Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8Meta · 1B
2.0 GB
1.0 GB
0.5 GB
Llama-3.2-1B-Instruct-QLORA_INT4_EO8Meta · 1B
2.0 GB
1.0 GB
0.5 GB
Llama-3.2-1BMeta · 1B
2.0 GB
1.0 GB
0.5 GB
Llama-3.2-1B-InstructMeta · 1B
2.0 GB
1.0 GB
0.5 GB
gemma-3-1b-itGoogle · 0.999886B
2.0 GB
1.0 GB
0.5 GB
MiniCPM5-1Bopenbmb · 1.08063B
2.2 GB
1.1 GB
0.5 GB
OpenELM-1_1B-Instructapple · 1.07989B
2.2 GB
1.1 GB
0.5 GB
TinyLlama-1.1B-Chat-v1.0TinyLlama · 1.10005B
2.2 GB
1.1 GB
0.6 GB
HunyuanOCRTencent · 1.11993B
2.2 GB
1.1 GB
0.6 GB
siglip2-so400m-patch14-384Google · 1.13601B
2.3 GB
1.1 GB
0.6 GB
Nemotron-3-Embed-1B-BF16NVIDIA · 1.14092B
2.3 GB
1.1 GB
0.6 GB
llama-nemotron-rerank-1b-v2NVIDIA · 1.23582B
2.5 GB
1.2 GB
0.6 GB
VGGT-1BMeta · 1.25654B
2.5 GB
1.3 GB
0.6 GB
MiniCPM-V-4.6openbmb · 1.30043B
2.6 GB
1.3 GB
0.7 GB
GLM-OCRZ.ai · 1.32526B
2.6 GB
1.3 GB
0.7 GB
privacy-filterOpenAI · 1.39949B
2.8 GB
1.4 GB
0.7 GB
stable-video-diffusion-img2vid-xtStability AI · 1.52462B
3.0 GB
1.5 GB
0.8 GB
whisper-large-v3OpenAI · 1.54349B
3.1 GB
1.5 GB
0.8 GB
Qwen2.5-1.5B-InstructQwen · 1.54371B
3.1 GB
1.5 GB
0.8 GB
jina-embeddings-v5-omni-smalljinaai · 1.62627B
3.2 GB
1.6 GB
0.8 GB
DeepSeek-R1-Distill-Qwen-1.5BDeepSeek · 1.77709B
3.5 GB
1.8 GB
0.9 GB
JiRackUltra_1bCMSManhattan · 1.77709B
3.5 GB
1.8 GB
0.9 GB
gte-Qwen2-1.5B-instructAlibaba-NLP · 1.7762B
3.5 GB
1.8 GB
0.9 GB
siglip2-giant-opt-patch16-384Google · 1.87189B
3.7 GB
1.9 GB
0.9 GB
Qwen3-TTS-12Hz-1.7B-BaseQwen · 1.92868B
3.9 GB
1.9 GB
1.0 GB
Qwen3-TTS-12Hz-1.7B-CustomVoiceQwen · 1.91668B
3.8 GB
1.9 GB
1.0 GB
moondream2vikhyatk · 1.92724B
3.9 GB
1.9 GB
1.0 GB
LTX-VideoLightricks · 1.92339B
3.9 GB
1.9 GB
1.0 GB
Qwen3-ASR-1.7B-hfQwen · 2B
4.0 GB
2.0 GB
1.0 GB
Qwen3.5-2B-BaseQwen · 2B
4.0 GB
2.0 GB
1.0 GB
Qwen3-1.7BQwen · 2.03174B
4.1 GB
2.0 GB
1.0 GB
Qwen3-VL-2B-InstructQwen · 2.12753B
4.3 GB
2.1 GB
1.1 GB
Qwen3-VL-Embedding-2BQwen · 2.12753B
4.3 GB
2.1 GB
1.1 GB
Qwen2-VL-2B-InstructQwen · 2.20899B
4.4 GB
2.2 GB
1.1 GB
InternVL2-2BOpenGVLab · 2.20575B
4.4 GB
2.2 GB
1.1 GB
Kimi-K3-DSparkRadixArk · 2.24929B
4.5 GB
2.2 GB
1.1 GB
Qwen3.5-2BQwen · 2.27407B
4.5 GB
2.3 GB
1.1 GB
VoxCPM2openbmb · 2.29B
4.6 GB
2.3 GB
1.1 GB
seamless-m4t-v2-largeMeta · 2.30925B
4.6 GB
2.3 GB
1.1 GB
Qwen3-ASR-1.7BQwen · 2.34922B
4.7 GB
2.4 GB
1.2 GB
Cosmos-Reason2-2BNVIDIA · 2.4387B
4.9 GB
2.4 GB
1.2 GB
MiniCPM5-2Bopenbmb · 2.51676B
5.0 GB
2.5 GB
1.3 GB
stable-diffusion-xl-base-1.0Stability AI · 2.56746B
5.1 GB
2.6 GB
1.3 GB
sdxl-turboStability AI · 2.56746B
5.1 GB
2.6 GB
1.3 GB
animagine-xl-4.0cagliostrolab · 2.56746B
5.1 GB
2.6 GB
1.3 GB
playground-v2.5-1024px-aestheticplaygroundai · 2.56746B
5.1 GB
2.6 GB
1.3 GB
RealVisXL_V5.0SG161222 · 2.56746B
5.1 GB
2.6 GB
1.3 GB
gemma-2-2b-itGoogle · 2.61434B
5.2 GB
2.6 GB
1.3 GB
VibeVoice-1.5BMicrosoft · 2.70402B
5.4 GB
2.7 GB
1.4 GB
phi-2Microsoft · 2.77968B
5.6 GB
2.8 GB
1.4 GB
Ministral-3-3B-Reasoning-2512-GGUFMistral AI · 3B
6.0 GB
3.0 GB
1.5 GB
Ministral-3-3B-Instruct-2512-GGUFMistral AI · 3B
6.0 GB
3.0 GB
1.5 GB
Llama-3.2-3B-Instruct-QLORA_INT4_EO8Meta · 3B
6.0 GB
3.0 GB
1.5 GB
Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8Meta · 3B
6.0 GB
3.0 GB
1.5 GB
Llama-3.2-3BMeta · 3B
6.0 GB
3.0 GB
1.5 GB
Llama-3.2-3B-InstructMeta · 3B
6.0 GB
3.0 GB
1.5 GB
dots.ocrdots-studio · 3.03918B
6.1 GB
3.0 GB
1.5 GB
Qwen2.5-3B-InstructQwen · 3.08594B
6.2 GB
3.1 GB
1.5 GB
SmolLM3-3BHuggingFaceTB · 3.0751B
6.2 GB
3.1 GB
1.5 GB
DeepSeek-OCRDeepSeek · 3.33611B
6.7 GB
3.3 GB
1.7 GB
Unlimited-OCRbaidu · 3.33611B
6.7 GB
3.3 GB
1.7 GB
DeepSeek-OCR-2DeepSeek · 3.38912B
6.8 GB
3.4 GB
1.7 GB
granite-4.1-3bIBM · 3.40284B
6.8 GB
3.4 GB
1.7 GB
Giga-Embeddings-instructai-sage · 3.44962B
6.9 GB
3.5 GB
1.7 GB
blip2-opt-2.7bSalesforce · 3.74476B
7.5 GB
3.7 GB
1.9 GB
Qwen2.5-VL-3B-InstructQwen · 3.75462B
7.5 GB
3.8 GB
1.9 GB
Phi-3.5-mini-instructMicrosoft · 3.82108B
7.6 GB
3.8 GB
1.9 GB
Phi-3-mini-4k-instructMicrosoft · 3.82108B
7.6 GB
3.8 GB
1.9 GB
Phi-4-mini-instructMicrosoft · 3.83602B
7.7 GB
3.8 GB
1.9 GB
Cosmos3-EdgeNVIDIA · 3.859B
7.7 GB
3.9 GB
1.9 GB
FLUX.2-klein-4BBlack Forest Labs · 3.87554B
7.8 GB
3.9 GB
1.9 GB
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA · 3.97356B
8.0 GB
4.0 GB
2.0 GB
Qwen3Guard-Stream-4BQwen · 4B
8.0 GB
4.0 GB
2.0 GB
Qwen3-Reranker-4BQwen · 4B
8.0 GB
4.0 GB
2.0 GB
Shieldstral-1.0-3BMistral AI · 4B
8.0 GB
4.0 GB
2.0 GB
Ministral-3-3B-Reasoning-2512Mistral AI · 4B
8.0 GB
4.0 GB
2.0 GB
Ministral-3-3B-Instruct-2512-BF16Mistral AI · 4B
8.0 GB
4.0 GB
2.0 GB
Ministral-3-3B-Instruct-2512Mistral AI · 4B
8.0 GB
4.0 GB
2.0 GB
Voxtral-4B-TTS-2603Mistral AI · 4B
8.0 GB
4.0 GB
2.0 GB
Voxtral-Mini-4B-Realtime-2602Mistral AI · 4B
8.0 GB
4.0 GB
2.0 GB
Ministral-3-3B-Instruct-2512-ONNXMistral AI · 4B
8.0 GB
4.0 GB
2.0 GB
Ministral-3-3B-Base-2512Mistral AI · 4B
8.0 GB
4.0 GB
2.0 GB
Qwen3-4BQwen · 4.02247B
8.0 GB
4.0 GB
2.0 GB
Qwen3-4B-Instruct-2507Qwen · 4.02247B
8.0 GB
4.0 GB
2.0 GB
Qwen3-Embedding-4BQwen · 4.02177B
8.0 GB
4.0 GB
2.0 GB
zerank-2-rerankerzeroentropy · 4.02247B
8.0 GB
4.0 GB
2.0 GB
Phi-3.5-vision-instructMicrosoft · 4.14662B
8.3 GB
4.2 GB
2.1 GB
gemma-3-4b-itGoogle · 4.30008B
8.6 GB
4.3 GB
2.1 GB
medgemma-4b-itGoogle · 4.30008B
8.6 GB
4.3 GB
2.1 GB
medgemma-1.5-4b-itGoogle · 4.30008B
8.6 GB
4.3 GB
2.1 GB
Qwen3-4B-Instruct-2507-FP8Qwen · 4.41165B
8.8 GB
4.4 GB
2.2 GB
Qwen3-VL-4B-InstructQwen · 4.43782B
8.9 GB
4.4 GB
2.2 GB
Qwen3.5-4BQwen · 4.65987B
9.3 GB
4.7 GB
2.3 GB
Qianfan-OCRbaidu · 4.74141B
9.5 GB
4.7 GB
2.4 GB
Qwen-Drive-1.0-4BQwen · 5B
10.0 GB
5.0 GB
2.5 GB
Qwen3.5-4B-BaseQwen · 5B
10.0 GB
5.0 GB
2.5 GB
Qwen2.5-VL-7B-Instruct-NVFP4NVIDIA · 5.02952B
10.1 GB
5.0 GB
2.5 GB
gemma-4-E2B-itGoogle · 5.12318B
10.2 GB
5.1 GB
2.6 GB
chandra-ocr-2datalab-to · 5.29556B
10.6 GB
5.3 GB
2.6 GB
Phi-4-multimodal-instructMicrosoft · 5.57446B
11.2 GB
5.6 GB
2.8 GB
Z-Image-TurboTongyi-MAI · 6.15491B
12.3 GB
6.2 GB
3.1 GB
ESMC-6Bbiohub · 6.35201B
12.7 GB
6.3 GB
3.2 GB
Llama-2-7b-hfMeta · 6.73842B
13.5 GB
6.7 GB
3.4 GB
Llama-2-7b-chat-hfMeta · 6.73842B
13.5 GB
6.7 GB
3.4 GB
CodeLlama-7b-hfcodellama · 6.73855B
13.5 GB
6.7 GB
3.4 GB
deepseek-coder-7b-instruct-v1.5DeepSeek · 6.91037B
13.8 GB
6.9 GB
3.5 GB
Qwen-Image-2.1Qwen · 7B
14.0 GB
7.0 GB
3.5 GB
pythia-6.9bEleutherAI · 6.99152B
14.0 GB
7.0 GB
3.5 GB
llava-1.5-7b-hfllava-hf · 7.06343B
14.1 GB
7.1 GB
3.5 GB
falcon-7bTechnology Innovation Institute · 7.21719B
14.4 GB
7.2 GB
3.6 GB
Mistral-7B-Instruct-v0.3Mistral AI · 7.24802B
14.5 GB
7.2 GB
3.6 GB
Mistral-7B-Instruct-v0.2Mistral AI · 7.24173B
14.5 GB
7.2 GB
3.6 GB
Mistral-7B-v0.1Mistral AI · 7.24173B
14.5 GB
7.2 GB
3.6 GB
Olmo-3-7B-InstructAllenAI · 7.29801B
14.6 GB
7.3 GB
3.6 GB
Qwen3-Embedding-8BQwen · 7.5673B
15.1 GB
7.6 GB
3.8 GB
Octen-Embedding-8BOcten · 7.5673B
15.1 GB
7.6 GB
3.8 GB
llava-v1.6-mistral-7b-hfllava-hf · 7.56675B
15.1 GB
7.6 GB
3.8 GB
Qwen2.5-7B-InstructQwen · 7.61562B
15.2 GB
7.6 GB
3.8 GB
Qwen2.5-Coder-7B-InstructQwen · 7.61562B
15.2 GB
7.6 GB
3.8 GB
Qwen2.5-7BQwen · 7.61562B
15.2 GB
7.6 GB
3.8 GB
zetazed-industries · 7.61562B
15.2 GB
7.6 GB
3.8 GB
Qwen3Guard-Stream-8BQwen · 8B
16.0 GB
8.0 GB
4.0 GB
Qwen3-Reranker-8BQwen · 8B
16.0 GB
8.0 GB
4.0 GB
Ministral-3-8B-Reasoning-2512-GGUFMistral AI · 8B
16.0 GB
8.0 GB
4.0 GB
Ministral-3-8B-Instruct-2512-GGUFMistral AI · 8B
16.0 GB
8.0 GB
4.0 GB
Meta-Llama-3-8B-InstructMeta · 8B
16.0 GB
8.0 GB
4.0 GB
Llama-3.1-8BMeta · 8B
16.0 GB
8.0 GB
4.0 GB
gemma-4-E4B-itGoogle · 7.99616B
16.0 GB
8.0 GB
4.0 GB
gemma-4-E4BGoogle · 7.99616B
16.0 GB
8.0 GB
4.0 GB
LLaDA-8B-InstructGSAI-ML · 8.01558B
16.0 GB
8.0 GB
4.0 GB
Llama-3.1-8B-InstructMeta · 8.03026B
16.1 GB
8.0 GB
4.0 GB
Meta-Llama-3-8BMeta · 8.03026B
16.1 GB
8.0 GB
4.0 GB
Hermes-3-Llama-3.1-8BNousResearch · 8.03026B
16.1 GB
8.0 GB
4.0 GB
Apertus-8B-Instruct-2509swiss-ai · 8.05334B
16.1 GB
8.1 GB
4.0 GB
Qwen3-VL-Embedding-8BQwen · 8.14479B
16.3 GB
8.1 GB
4.1 GB
Qwen3-8BQwen · 8.19074B
16.4 GB
8.2 GB
4.1 GB
DeepSeek-R1-0528-Qwen3-8BDeepSeek · 8.19074B
16.4 GB
8.2 GB
4.1 GB
Qwen2.5-VL-7B-InstructQwen · 8.29217B
16.6 GB
8.3 GB
4.2 GB
Qwen2-VL-7B-InstructQwen · 8.29138B
16.6 GB
8.3 GB
4.2 GB
UI-TARS-1.5-7BByteDance-Seed · 8.29217B
16.6 GB
8.3 GB
4.2 GB
NuMarkdown-8B-Thinkingnumind · 8.29217B
16.6 GB
8.3 GB
4.2 GB
personaplex-7b-v1NVIDIA · 8.37141B
16.7 GB
8.4 GB
4.2 GB
VibeVoice-ASRMicrosoft · 8.67402B
17.4 GB
8.7 GB
4.3 GB
MiniCPM-o-2_6openbmb · 8.675B
17.4 GB
8.7 GB
4.3 GB
Qwen3-VL-8B-InstructQwen · 8.76712B
17.5 GB
8.8 GB
4.4 GB
Qwen3-VL-8B-Instruct-FP8Qwen · 8.76755B
17.5 GB
8.8 GB
4.4 GB
chandradatalab-to · 8.76712B
17.5 GB
8.8 GB
4.4 GB
NVIDIA-Nemotron-Nano-9B-v2NVIDIA · 8.88823B
17.8 GB
8.9 GB
4.4 GB
Apertus-v1.5-8Bswiss-ai · 8.90355B
17.8 GB
8.9 GB
4.5 GB
Qwen-Image-2.1-PE-I2IQwen · 9B
18.0 GB
9.0 GB
4.5 GB
Qwen-Image-2.1-PE-T2IQwen · 9B
18.0 GB
9.0 GB
4.5 GB
Ministral-3-8B-Reasoning-2512Mistral AI · 9B
18.0 GB
9.0 GB
4.5 GB
Ministral-3-8B-Instruct-2512-BF16Mistral AI · 9B
18.0 GB
9.0 GB
4.5 GB
Ministral-3-8B-Instruct-2512Mistral AI · 9B
18.0 GB
9.0 GB
4.5 GB
Ministral-3-8B-Base-2512Mistral AI · 9B
18.0 GB
9.0 GB
4.5 GB
gemma-2-9b-itGoogle · 9.24171B
18.5 GB
9.2 GB
4.6 GB
MiniCPM-o-4_5openbmb · 9.37179B
18.7 GB
9.4 GB
4.7 GB
Qwen3.5-9BQwen · 9.6531B
19.3 GB
9.7 GB
4.8 GB
Ornith-1.5-9Bornith-ai · 9.6531B
19.3 GB
9.7 GB
4.8 GB
Qwen3.5-9B-BaseQwen · 10B
20.0 GB
10.0 GB
5.0 GB
Llama-3.2-11B-Vision-InstructMeta · 11B
22.0 GB
11.0 GB
5.5 GB
Llama-Guard-3-11B-VisionMeta · 11B
22.0 GB
11.0 GB
5.5 GB
FLUX.1-devBlack Forest Labs · 11.9014B
23.8 GB
11.9 GB
6.0 GB
FLUX.1-schnellBlack Forest Labs · 11.8912B
23.8 GB
11.9 GB
6.0 GB
FLUX.1-Kontext-devBlack Forest Labs · 11.9014B
23.8 GB
11.9 GB
6.0 GB
gemma-4-12B-itGoogle · 11.9597B
23.9 GB
12.0 GB
6.0 GB
Pixtral-12B-2409Mistral AI · 12B
24.0 GB
12.0 GB
6.0 GB
Llama-Guard-4-12BMeta · 12B
24.0 GB
12.0 GB
6.0 GB
gemma-3-12b-itGoogle · 12.1873B
24.4 GB
12.2 GB
6.1 GB
Mistral-Nemo-Instruct-2407Mistral AI · 12.2478B
24.5 GB
12.2 GB
6.1 GB
gemma-4-12B-it-qat-w4a16-ctGoogle · 13.307B
26.6 GB
13.3 GB
6.7 GB
Ministral-3-14B-Reasoning-2512Mistral AI · 14B
28.0 GB
14.0 GB
7.0 GB
Ministral-3-14B-Instruct-2512-BF16Mistral AI · 14B
28.0 GB
14.0 GB
7.0 GB
Ministral-3-14B-Instruct-2512Mistral AI · 14B
28.0 GB
14.0 GB
7.0 GB
Ministral-3-14B-Instruct-2512-GGUFMistral AI · 14B
28.0 GB
14.0 GB
7.0 GB
Ministral-3-14B-Base-2512Mistral AI · 14B
28.0 GB
14.0 GB
7.0 GB
Gemma-4-26B-A4B-NVFP4NVIDIA · 14.3869B
28.8 GB
14.4 GB
7.2 GB
Qwen3.8-27B-NVFP4-RTX5090gittensor-model-hub · 14.5575B
29.1 GB
14.6 GB
7.3 GB
phi-4Microsoft · 14.6595B
29.3 GB
14.7 GB
7.3 GB
Qwen3-14BQwen · 14.7683B
29.5 GB
14.8 GB
7.4 GB
Qwen2.5-14B-InstructQwen · 14.77B
29.5 GB
14.8 GB
7.4 GB
Qwen2.5-Coder-14B-InstructQwen · 14.77B
29.5 GB
14.8 GB
7.4 GB
DeepSeek-R1-Distill-Qwen-14BDeepSeek · 14.77B
29.5 GB
14.8 GB
7.4 GB
DeepSeek-Coder-V2-Lite-InstructDeepSeek · 15.7065B
31.4 GB
15.7 GB
7.8 GB
Qwen3.8-27B-NVFP4Inferact · 17.6312B
35.3 GB
17.6 GB
8.8 GB
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4NVIDIA · 17.8202B
35.6 GB
17.8 GB
8.9 GB
Qwen3.8-27B-NVFP4RadixArk · 18.1646B
36.3 GB
18.2 GB
9.1 GB
Qwen3.6-27B-NVFP4NVIDIA · 18.1646B
36.3 GB
18.2 GB
9.1 GB
Qwen3.8-27B-NVFP4NVIDIA · 18.1646B
36.3 GB
18.2 GB
9.1 GB
NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4NVIDIA · 18.2378B
36.5 GB
18.2 GB
9.1 GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4NVIDIA · 18.3263B
36.6 GB
18.3 GB
9.2 GB
Qwen3.6-35B-A3B-NVFP4NVIDIA · 18.6839B
37.4 GB
18.7 GB
9.3 GB
LTX-2Lightricks · 18.8762B
37.8 GB
18.9 GB
9.4 GB
Ornith-1.5-35B-A3B-NVFP4ornith-ai · 19.5285B
39.1 GB
19.5 GB
9.8 GB
Qwen3.8-27B-NVFP4unsloth · 19.8699B
39.7 GB
19.9 GB
9.9 GB
gpt-neox-20bEleutherAI · 20.7391B
41.5 GB
20.7 GB
10.4 GB
Gemma-4-31B-IT-NVFP4NVIDIA · 20.8686B
41.7 GB
20.9 GB
10.4 GB
gpt-oss-20bOpenAI · 20.9148B
41.8 GB
20.9 GB
10.5 GB
Qwen3.6-27B-NVFP4unsloth · 21.2324B
42.5 GB
21.2 GB
10.6 GB
Qwen3.6-35B-A3B-NVFP4-Fastunsloth · 21.8048B
43.6 GB
21.8 GB
10.9 GB
Devstral-Small-2-24B-Instruct-2512Mistral AI · 24B
48.0 GB
24.0 GB
12.0 GB
Magistral-Small-2509Mistral AI · 24B
48.0 GB
24.0 GB
12.0 GB
Mistral-Small-3.2-24B-Instruct-2506Mistral AI · 24B
48.0 GB
24.0 GB
12.0 GB
Mistral-Small-3.1-24B-Instruct-2503Mistral AI · 24.0114B
48.0 GB
24.0 GB
12.0 GB
Qwen3.6-35B-A3B-NVFP4unsloth · 24.6406B
49.3 GB
24.6 GB
12.3 GB
gemma-4-26B-A4B-itGoogle · 25.8059B
51.6 GB
25.8 GB
12.9 GB
diffusiongemma-26B-A4B-itGoogle · 25.8238B
51.6 GB
25.8 GB
12.9 GB
gemma-4-26B-A4B-it-FP8-dynamicRedHatAI · 26.5441B
53.1 GB
26.5 GB
13.3 GB
Gemma 3 27B ITGoogle · 27B
54.0 GB
27.0 GB
13.5 GB
Qwen-Image-BenchQwen · 27B
54.0 GB
27.0 GB
13.5 GB
Qwen3.8-27B-INT4RedHatAI · 27.3567B
54.7 GB
27.4 GB
13.7 GB
Qwen3.5-27BQwen · 27.7814B
55.6 GB
27.8 GB
13.9 GB
Qwen3.8-27B-OBLITERATEDOBLITERATUS · 27.7814B
55.6 GB
27.8 GB
13.9 GB
Qwen3.8-27B-Uncensored-FP8orcarouter · 27.7814B
55.6 GB
27.8 GB
13.9 GB
Qwen3.8-27BQwen · 28B
56.0 GB
28.0 GB
14.0 GB
Qwen3.8-27B-FP8Qwen · 28B
56.0 GB
28.0 GB
14.0 GB
Qwen3.6-27B-FP8Qwen · 28B
56.0 GB
28.0 GB
14.0 GB
Qwen3.6-27BQwen · 28B
56.0 GB
28.0 GB
14.0 GB
Qwen3.5-27B-GPTQ-Int4Qwen · 28B
56.0 GB
28.0 GB
14.0 GB
Qwen3.5-27B-FP8Qwen · 28B
56.0 GB
28.0 GB
14.0 GB
Muse-Glimmer-30Bmeta-models · 29.7766B
59.5 GB
29.8 GB
14.9 GB
Qwen3-30B-A3BQwen · 30.5321B
61.1 GB
30.5 GB
15.3 GB
Qwen3-30B-A3B-Instruct-2507Qwen · 30.5321B
61.1 GB
30.5 GB
15.3 GB
Qwen3-Coder-30B-A3B-Instruct-FP8Qwen · 30.5339B
61.1 GB
30.5 GB
15.3 GB
Qwen3-Coder-30B-A3B-InstructQwen · 30.5321B
61.1 GB
30.5 GB
15.3 GB
NVIDIA Nemotron 3 Nano 30B-A3BNVIDIA · 31B total / ~3B active
62.0 GB
31.0 GB
15.5 GB
GLM-4.7-FlashZ.ai · 31.2215B
62.4 GB
31.2 GB
15.6 GB
gemma-4-31B-itGoogle · 31.2731B
62.5 GB
31.3 GB
15.6 GB
OTel-2.0-LLM-31B-ITfarbodtavakkoli · 31.2731B
62.5 GB
31.3 GB
15.6 GB
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA · 31.5779B
63.2 GB
31.6 GB
15.8 GB
FLUX.2-devBlack Forest Labs · 32.2233B
64.5 GB
32.2 GB
16.1 GB
gemma-4-31B-it-NVFP4-turboLilaRest · 32.5278B
65.1 GB
32.5 GB
16.3 GB
gemma-4-31BGoogle · 32.6824B
65.4 GB
32.7 GB
16.3 GB
Qwen2.5-32B-InstructQwen · 32.7639B
65.5 GB
32.8 GB
16.4 GB
Qwen2.5-Coder-32B-InstructQwen · 32.7639B
65.5 GB
32.8 GB
16.4 GB
DeepSeek-R1-Distill-Qwen-32BDeepSeek · 32.7639B
65.5 GB
32.8 GB
16.4 GB
Qwen3-32BQwen · 32.8B
65.6 GB
32.8 GB
16.4 GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8NVIDIA · 33.0137B
66.0 GB
33.0 GB
16.5 GB
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16NVIDIA · 33.0156B
66.0 GB
33.0 GB
16.5 GB
MiniMax-H3MiniMax · 33.123B
66.2 GB
33.1 GB
16.6 GB
Qwen2.5-VL-32B-InstructQwen · 33.4527B
66.9 GB
33.5 GB
16.7 GB
dolphin-2.9.1-yi-1.5-34bdphn · 34.3889B
68.8 GB
34.4 GB
17.2 GB
Qwen3.6-35B-A3B-NVFP4RedHatAI · 34.6606B
69.3 GB
34.7 GB
17.3 GB
Qwen-AgentWorld-35B-A3BQwen · 35B
70.0 GB
35.0 GB
17.5 GB
FastVideo-FastH3-4-step-Preview-v1-VSA-DataFreeFastVideo · 35.0498B
70.1 GB
35.0 GB
17.5 GB
Qwen3-Omni-30B-A3B-InstructQwen · 35.2598B
70.5 GB
35.3 GB
17.6 GB
Qwen3.6-35B-A3BQwen · 35.9518B
71.9 GB
36.0 GB
18.0 GB
Ornith-1.5-35B-A3Bornith-ai · 35.9518B
71.9 GB
36.0 GB
18.0 GB
Qwen3.6-35B-A3B-FP8Qwen · 36B
72.0 GB
36.0 GB
18.0 GB
Qwen3.5-35B-A3B-GPTQ-Int4Qwen · 36B
72.0 GB
36.0 GB
18.0 GB
Qwen3.5-35B-A3B-FP8Qwen · 36B
72.0 GB
36.0 GB
18.0 GB
Qwen3.5-35B-A3BQwen · 36B
72.0 GB
36.0 GB
18.0 GB
Qwen3.5-35B-A3B-BaseQwen · 36B
72.0 GB
36.0 GB
18.0 GB
Mixtral-8x7B-Instruct-v0.1Mistral AI · 46.7028B
93.4 GB
46.7 GB
23.4 GB
Qwen3.5-122B-A10B-NVFP4NVIDIA · 64.5808B
129.2 GB
64.6 GB
32.3 GB
NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4NVIDIA · 67.2286B
134.5 GB
67.2 GB
33.6 GB
Llama 3.3 70B InstructMeta · 71B
142.0 GB
71.0 GB
35.5 GB
Meta-Llama-3-70B-InstructMeta · 71B
142.0 GB
71.0 GB
35.5 GB
Llama-3.1-70B-InstructMeta · 71B
142.0 GB
71.0 GB
35.5 GB
Qwen-72BQwen · 72.2879B
144.6 GB
72.3 GB
36.1 GB
Qwen3-Coder-NextQwen · 79.6744B
159.3 GB
79.7 GB
39.8 GB
Qwen3-Coder-Next-FP8Qwen · 79.6792B
159.4 GB
79.7 GB
39.8 GB
Llama-3.2-90B-Vision-InstructMeta · 89B
178.0 GB
89.0 GB
44.5 GB
Llama-4-Scout-17B-16E-InstructMeta · 109B
218.0 GB
109.0 GB
54.5 GB
Llama-4-Scout-17B-16EMeta · 109B
218.0 GB
109.0 GB
54.5 GB
Llama-4-Scout-17B-16E-OriginalMeta · 109B
218.0 GB
109.0 GB
54.5 GB
Llama-4-Scout-17B-16E-Instruct-OriginalMeta · 109B
218.0 GB
109.0 GB
54.5 GB
GLM-4.5-AirZ.ai · 110.469B
220.9 GB
110.5 GB
55.2 GB
gpt-oss-120bOpenAI · 117B total / 5.1B active
234.0 GB
117.0 GB
58.5 GB
Mistral Small 4 119B A6BMistral AI · 119B total / 6.5B active
238.0 GB
119.0 GB
59.5 GB
Leanstral-1.5-119B-A6BMistral AI · 119B
238.0 GB
119.0 GB
59.5 GB
Mistral-Small-4-119B-2603-eagleMistral AI · 119B
238.0 GB
119.0 GB
59.5 GB
NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA · 123.611B
247.2 GB
123.6 GB
61.8 GB
Devstral-2-123B-Instruct-2512Mistral AI · 125B
250.0 GB
125.0 GB
62.5 GB
Qwen3.5-122B-A10BQwen · 125.086B
250.2 GB
125.1 GB
62.5 GB
Mistral-Medium-3.5-128BMistral AI · 128B
256.0 GB
128.0 GB
64.0 GB
Mistral-Medium-3.5-128B-EAGLEMistral AI · 128B
256.0 GB
128.0 GB
64.0 GB
DeepSeek-V4-Flash-DSparkDeepSeek · 165.265B
330.5 GB
165.3 GB
82.6 GB
Qwen3.8-Flash-Next-FP8Qwen · 180B
360.0 GB
180.0 GB
90.0 GB
Qwen3.8-Flash-NextQwen · 180B
360.0 GB
180.0 GB
90.0 GB
MiniMax-M2.7MiniMax · 228.69B
457.4 GB
228.7 GB
114.3 GB
MiniMax-M2MiniMax · 228.69B
457.4 GB
228.7 GB
114.3 GB
MiniMax-M2.5MiniMax · 228.704B
457.4 GB
228.7 GB
114.3 GB
Qwen3-235B-A22BQwen · 235.094B
470.2 GB
235.1 GB
117.5 GB
Inkling-Smallthinkingmachines · 265.956B
531.9 GB
266.0 GB
133.0 GB
DeepSeek-V4-FlashDeepSeek · 290.945B
581.9 GB
290.9 GB
145.5 GB
Hy3Tencent · 298.786B
597.6 GB
298.8 GB
149.4 GB
DeepSeek-V4-Flash-0731DeepSeek · 304.18B
608.4 GB
304.2 GB
152.1 GB
DeepSeek-V4-Flash-Vision-ExpDeepSeek · 304.647B
609.3 GB
304.6 GB
152.3 GB
GLM-5.3-FlashZ.ai · 321.323B
642.6 GB
321.3 GB
160.7 GB
GLM-5.2-NVFP4NVIDIA · 380.989B
762.0 GB
381.0 GB
190.5 GB
Llama-4-Maverick-17B-128E-InstructMeta · 402B
804.0 GB
402.0 GB
201.0 GB
Llama-4-Maverick-17B-128E-Instruct-FP8Meta · 402B
804.0 GB
402.0 GB
201.0 GB
Llama-4-Maverick-17B-128E-Instruct-OriginalMeta · 402B
804.0 GB
402.0 GB
201.0 GB
Llama-4-Maverick-17B-128EMeta · 402B
804.0 GB
402.0 GB
201.0 GB
Llama-4-Maverick-17B-128E-OriginalMeta · 402B
804.0 GB
402.0 GB
201.0 GB
Llama-4-Maverick-17B-128E-Instruct-FP8-OriginalMeta · 402B
804.0 GB
402.0 GB
201.0 GB
Qwen3.5-397B-A17BQwen · 403.398B
806.8 GB
403.4 GB
201.7 GB
Qwen3.5-397B-A17B-FP8Qwen · 403.422B
806.8 GB
403.4 GB
201.7 GB
Llama-3.1-405B-FP8Meta · 406B
812.0 GB
406.0 GB
203.0 GB
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA · 560.525B
1,121.0 GB
560.5 GB
280.3 GB
DeepSeek-R1DeepSeek · 671B total / 37B active
1,342.0 GB
671.0 GB
335.5 GB
Mistral-Large-3-675B-Instruct-2512-NVFP4Mistral AI · 675B
1,350.0 GB
675.0 GB
337.5 GB
Mistral-Large-3-675B-Instruct-2512-EagleMistral AI · 675B
1,350.0 GB
675.0 GB
337.5 GB
Mistral-Large-3-675B-Instruct-2512Mistral AI · 675B
1,350.0 GB
675.0 GB
337.5 GB
DeepSeek-V3-0324DeepSeek · 684.531B
1,369.1 GB
684.5 GB
342.3 GB
DeepSeek-V3DeepSeek · 684.531B
1,369.1 GB
684.5 GB
342.3 GB
DeepSeek-V3.1DeepSeek · 684.531B
1,369.1 GB
684.5 GB
342.3 GB
DeepSeek-V3.2DeepSeek · 685.355B
1,370.7 GB
685.4 GB
342.7 GB
GLM-5.3Z.ai · 753.33B
1,506.7 GB
753.3 GB
376.7 GB
GLM-5.2Z.ai · 753.33B
1,506.7 GB
753.3 GB
376.7 GB
GLM-5.2-FP8Z.ai · 753.33B
1,506.7 GB
753.3 GB
376.7 GB
GLM-5Z.ai · 753.864B
1,507.7 GB
753.9 GB
376.9 GB
GLM-5.1Z.ai · 753.864B
1,507.7 GB
753.9 GB
376.9 GB
DeepSeek-V4.1-FlashDeepSeek · 763.205B
1,526.4 GB
763.2 GB
381.6 GB
Inklingthinkingmachines · 952.378B
1,904.8 GB
952.4 GB
476.2 GB
Kimi-K2-InstructMoonshot AI · 1026.41B
2,052.8 GB
1,026.4 GB
513.2 GB
Kimi-K2.6Moonshot AI · 1026.88B
2,053.8 GB
1,026.9 GB
513.4 GB
DeepSeek-V4-ProDeepSeek · 1598.84B
3,197.7 GB
1,598.8 GB
799.4 GB
Qwen3.8-2.4T-A95BQwen · 2.4T
4,800.0 GB
2,400.0 GB
1,200.0 GB
Qwen3.8-2.4T-A95B-FP8Qwen · 2.4T
4,800.0 GB
2,400.0 GB
1,200.0 GB
Kimi-K3Moonshot AI · 2779.93B
5,559.9 GB
2,779.9 GB
1,390.0 GB
Decimal GB estimate: parameter count × bytes per weight. This is a comparison aid, not a deployment guarantee.