{ "id": "nvidia-glm-5-2-nvfp4", "name": "GLM-5.2-NVFP4", "developer": "NVIDIA", "family": "GLM-5.2-NVFP4", "variant": "GLM-5.2-NVFP4", "model": { "parameters": "380.989B", "total_parameters_billions": 380.989135104, "context": { "value": 1048576, "display": "1,048,576 tokens", "status": "verified", "evidence": [ { "source": "config.json", "detail": "max_position_embeddings" } ] }, "modality": "Text", "tags": [ "Model Optimizer", "safetensors", "glm_moe_dsa", "nvidia", "ModelOpt", "GLM-5", "quantized", "4-bit precision", "FP4", "fp4", "text-generation", "conversational", "base_model:zai-org/GLM-5.2", "base_model:quantized:zai-org/GLM-5.2", "license:mit", "8-bit", "modelopt", "region:us" ] }, "weights": { "status": "verified-available", "repository": "https://huggingface.co/nvidia/GLM-5.2-NVFP4", "access": "public", "exact_files": [ "model-00001-of-00047.safetensors", "model-00002-of-00047.safetensors", "model-00003-of-00047.safetensors", "model-00004-of-00047.safetensors", "model-00005-of-00047.safetensors", "model-00006-of-00047.safetensors", "model-00007-of-00047.safetensors", "model-00008-of-00047.safetensors", "model-00009-of-00047.safetensors", "model-00010-of-00047.safetensors", "model-00011-of-00047.safetensors", "model-00012-of-00047.safetensors", "model-00013-of-00047.safetensors", "model-00014-of-00047.safetensors", "model-00015-of-00047.safetensors", "model-00016-of-00047.safetensors", "model-00017-of-00047.safetensors", "model-00018-of-00047.safetensors", "model-00019-of-00047.safetensors", "model-00020-of-00047.safetensors", "model-00021-of-00047.safetensors", "model-00022-of-00047.safetensors", "model-00023-of-00047.safetensors", "model-00024-of-00047.safetensors", "model-00025-of-00047.safetensors", "model-00026-of-00047.safetensors", "model-00027-of-00047.safetensors", "model-00028-of-00047.safetensors", "model-00029-of-00047.safetensors", "model-00030-of-00047.safetensors", "model-00031-of-00047.safetensors", "model-00032-of-00047.safetensors", "model-00033-of-00047.safetensors", "model-00034-of-00047.safetensors", "model-00035-of-00047.safetensors", "model-00036-of-00047.safetensors", "model-00037-of-00047.safetensors", "model-00038-of-00047.safetensors", "model-00039-of-00047.safetensors", "model-00040-of-00047.safetensors", "model-00041-of-00047.safetensors", "model-00042-of-00047.safetensors", "model-00043-of-00047.safetensors", "model-00044-of-00047.safetensors", "model-00045-of-00047.safetensors", "model-00046-of-00047.safetensors", "model-00047-of-00047.safetensors", "model.safetensors.index.json" ], "file_count": 48, "formats": [ "Safetensors" ], "precision_availability": { "bf16": { "available": true, "status": "verified" }, "fp16": { "available": false, "status": "verified" }, "fp8": { "available": false, "status": "verified" }, "int8": { "available": false, "status": "verified" }, "int4": { "available": false, "status": "verified" }, "gguf": { "available": false, "status": "verified" } }, "dtype_evidence": [ "BF16", "BFLOAT16", "F32", "U8" ], "evidence": [ { "source": "https://huggingface.co/api/models/nvidia/GLM-5.2-NVFP4", "type": "Hugging Face model API siblings" } ] }, "license": { "id": "mit", "name": "MIT", "url": null, "status": "verified", "commercial_use": { "status": "allowed", "label": "Commercial use allowed under MIT conditions", "basis": null }, "repository_license_files": [], "verification": { "status": "metadata-only", "checked_at": "2026-10-03", "source": null } }, "hardware": { "status": "estimated", "weight_only_gb": { "bf16_fp16": 761.98, "fp8_int8": 380.99, "int4": 190.49 }, "note": "Weight-only decimal-GB estimate from total parameter count; excludes KV cache, activations, runtime overhead, optimizer state and sharding." }, "lineage": { "family": "GLM-5.2-NVFP4", "variant": "GLM-5.2-NVFP4", "base_model": { "status": "declared", "models": [ "zai-org/GLM-5.2" ], "relation": null, "evidence": [ { "source": "model-card metadata", "field": "base_model" } ] } }, "training_assets": { "training_recipe": { "status": "training-described-in-model-card", "files": [], "links": [], "evidence": [ "README.md" ] }, "data_disclosure": { "status": "described-in-model-card", "datasets": [], "evidence": [ { "source": "README.md", "detail": "data/dataset section present" } ] }, "evaluations": "Not classified by automated verifier", "intermediate_checkpoints": "Not classified by automated verifier" }, "sources": [ { "type": "model_repository", "url": "https://huggingface.co/nvidia/GLM-5.2-NVFP4", "tier": "primary" }, { "type": "model_api", "url": "https://huggingface.co/api/models/nvidia/GLM-5.2-NVFP4", "tier": "primary" }, { "type": "model_card", "url": "https://huggingface.co/nvidia/GLM-5.2-NVFP4/blob/main/README.md", "tier": "primary", "available": true }, { "type": "config", "url": "https://huggingface.co/nvidia/GLM-5.2-NVFP4/blob/main/config.json", "tier": "primary", "available": true } ], "verification": { "level": "field-verified", "checked_at": "2026-10-03", "checked_at_iso": "2026-10-03T10:33:40+00:00", "method": "Hugging Face API + repository file list + model card + config.json", "mode": "repository-revision-unchanged", "full_verified_at": "2026-10-03", "readme_accessible": true, "config_accessible": true, "fields": { "license": "verified", "commercial_use": "classified", "context": "verified", "weight_files": "verified", "formats": "verified", "base_model": "declared", "training_recipe": "training-described-in-model-card", "data_disclosure": "described-in-model-card", "runtime_support": "source-derived-not-runtime-tested" }, "history": [ { "date": "2026-10-03", "event": "Repository revision check", "detail": "Official Hugging Face repository SHA unchanged; prior field evidence retained." }, { "date": "2026-10-03", "event": "Field-by-field verification", "detail": "Checked Hugging Face API metadata, exact repository file list, model card and config when accessible." }, { "date": "2026-10-03", "event": "Registry record created", "detail": "Previous verification level: discovered-pending." } ] }, "discovery": { "source": "Hugging Face public model index", "repo_id": "nvidia/GLM-5.2-NVFP4", "rank": 521, "downloads": 526328, "likes": 323, "last_modified": "2026-08-31T15:59:10+00:00", "created_at": "2026-06-22T19:55:57+00:00", "library_name": "Model Optimizer", "pipeline_tag": "text-generation", "discovered_at": "2026-10-03T10:33:38+00:00", "pinned": false }, "runtime_support": { "declared_library": "Model Optimizer", "pipeline_tag": "text-generation", "declared": [ "Model Optimizer" ], "mentioned_in_model_card": [ "SGLang", "Transformers", "vLLM" ], "artifact_signals": [], "tested_by_openmodelweights": false }, "hub": { "last_modified": "2026-08-31T15:59:10.000Z", "created_at": "2026-06-22T19:55:57.000Z", "downloads": 526328, "likes": 323, "sha": "53e0691e21895a3863a606dfd12910c69eba94ab", "library_name": "Model Optimizer", "pipeline_tag": "text-generation", "tags": [ "Model Optimizer", "safetensors", "glm_moe_dsa", "nvidia", "ModelOpt", "GLM-5", "quantized", "4-bit precision", "FP4", "fp4", "text-generation", "conversational", "base_model:zai-org/GLM-5.2", "base_model:quantized:zai-org/GLM-5.2", "license:mit", "8-bit", "modelopt", "region:us" ] } }