{"model_id": "antirez/deepseek-v4-gguf", "name": "deepseek-v4-gguf", "owner": "antirez", "source_url": "https://huggingface.co/antirez/deepseek-v4-gguf", "task": "text-generation", "languages": ["en"], "tags": ["gguf", "quantized", "deepseek", "deepseek-v4", "deepseek-v4-flash", "moe", "mixture-of-experts", "2-bit", "4-bit", "iq2_xxs", "q2_k", "q4_k", "ds4", "apple-silicon", "metal", "text-generation", "en", "base_model:deepseek-ai/DeepSeek-V4-Flash", "base_model:quantized:deepseek-ai/DeepSeek-V4-Flash", "license:mit", "endpoints_compatible", "region:us", "conversational"], "license_id": "mit", "license_status": "ouverte_permissive", "license_label": "MIT License", "commercial_use": "possible_a_verifier", "gated": false, "private": false, "downloads": 1474568, "likes": 486, "updated_at": "2026-08-31T18:47:37.000Z", "description": "", "files": [{"name": ".gitattributes", "size": 4173, "format": "autre", "precision": "inconnue"}, {"name": "DeepSeek-V4-Flash-DSpark-support-0731.gguf", "size": 5989114272, "format": "gguf", "precision": "inconnue"}, {"name": "DeepSeek-V4-Flash-DSpark-support.gguf", "size": 5989114272, "format": "gguf", "precision": "inconnue"}, {"name": "DeepSeek-V4-Flash-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-chat-v2-imatrix-0731.gguf", "size": 86720111488, "format": "gguf", "precision": "8-bit"}, {"name": "DeepSeek-V4-Flash-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-chat-v2-imatrix.gguf", "size": 86720111488, "format": "gguf", "precision": "8-bit"}, {"name": "DeepSeek-V4-Flash-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-chat-v2.gguf", "size": 86720111200, "format": "gguf", "precision": "8-bit"}, {"name": "DeepSeek-V4-Flash-Layers37-42Q4KExperts-OtherExpertLayersIQ2XXSGateUp-Q2KDown-AProjQ8-SExpQ8-OutQ8-chat-v2-imatrix-fixed-0731.gguf", "size": 97591747456, "format": "gguf", "precision": "4-bit"}, {"name": "DeepSeek-V4-Flash-Layers37-42Q4KExperts-OtherExpertLayersIQ2XXSGateUp-Q2KDown-AProjQ8-SExpQ8-OutQ8-chat-v2-imatrix-fixed.gguf", "size": 97591747456, "format": "gguf", "precision": "4-bit"}, {"name": "DeepSeek-V4-Flash-MTP-Q4K-Q8_0-F32.gguf", "size": 3807602400, "format": "gguf", "precision": "4-bit"}, {"name": "DeepSeek-V4-Flash-MXFP4Experts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-chat-v2-mxfp4-0731.gguf", "size": 155976458848, "format": "gguf", "precision": "8-bit"}, {"name": "DeepSeek-V4-Flash-Q4KExperts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-chat-v2-imatrix-0731.gguf", "size": 164633502592, "format": "gguf", "precision": "4-bit"}, {"name": "DeepSeek-V4-Flash-Q4KExperts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-chat-v2-imatrix.gguf", "size": 164633502592, "format": "gguf", "precision": "4-bit"}, {"name": "DeepSeek-V4-Flash-Q4KExperts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-chat-v2.gguf", "size": 164633502304, "format": "gguf", "precision": "4-bit"}, {"name": "DeepSeek-V4-Flash-Vision-Encoder.gguf", "size": 932857760, "format": "gguf", "precision": "inconnue"}, {"name": "DeepSeek-V4-Flash-Vision-Exp-DSpark-support.gguf", "size": 5989114528, "format": "gguf", "precision": "inconnue"}, {"name": "DeepSeek-V4-Flash-Vision-Exp-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8.gguf", "size": 86720111776, "format": "gguf", "precision": "8-bit"}, {"name": "DeepSeek-V4-Flash-Vision-Exp-Layers37-42Q4KExperts-OtherExpertLayersIQ2XXSGateUp-Q2KDown-AProjQ8-SExpQ8-OutQ8.gguf", "size": 97591747744, "format": "gguf", "precision": "4-bit"}, {"name": "DeepSeek-V4-Flash-Vision-Exp-MXFP4Experts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out.gguf", "size": 155976459136, "format": "gguf", "precision": "8-bit"}, {"name": "DeepSeek-V4-Pro-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-Instruct-imatrix-0813.gguf", "size": 464627334560, "format": "gguf", "precision": "8-bit"}, {"name": "DeepSeek-V4-Pro-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-Instruct-imatrix.gguf", "size": 464627334560, "format": "gguf", "precision": "8-bit"}, {"name": "DeepSeek-V4-Pro-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-Instruct.gguf", "size": 464627334240, "format": "gguf", "precision": "8-bit"}, {"name": "DeepSeek-V4-Pro-Q4K-Layers-31-output.gguf", "size": 441962533120, "format": "gguf", "precision": "4-bit"}, {"name": "DeepSeek-V4-Pro-Q4K-Layers00-30.gguf", "size": 457521327328, "format": "gguf", "precision": "4-bit"}, {"name": "README.md", "size": 3528, "format": "autre", "precision": "inconnue"}, {"name": "imatrix/DeepSeek-V4-Flash-chat-v2-routed-moe-ds4-1p5m.dat", "size": 450892648, "format": "autre", "precision": "inconnue"}], "parameter_count": null, "library_name": "gguf", "pipeline_tag": "text-generation", "datasets": [], "metrics": [], "github_url": "", "github_metadata": {}, "paper_url": "", "paper_doi": "", "paper_metadata": {}, "card_complete": true, "safetensors": false, "provenance": [{"source": "Hugging Face Hub API", "url": "https://huggingface.co/antirez/deepseek-v4-gguf", "retrieved_at": "2026-10-16T02:03:37.250742+00:00"}], "retrieved_at": "2026-10-16T02:03:37.250742+00:00", "warnings": ["La licence est déclarée par le producteur ; vérifiez toujours son texte intégral et les conditions associées.", "Plusieurs variantes GGUF sont publiées : l’estimation retient la plus petite taille connue, pas leur somme."], "rank_score": 0.0, "rank_reasons": [], "compatibility": {"state": "compatible", "label": "Compatible selon l’estimation", "summary": "La mémoire indiquée dépasse l’estimation prudente.", "factors": ["Mémoire estimée : 1.1 Go, marge d’exécution de 30% incluse.", "Espace disque minimal indicatif : 0.9 Go.", "Une exécution CPU peut être possible mais sa vitesse ne peut pas être déduite de ces métadonnées."], "estimate": {"known": true, "precision": "4-bit", "source": "taille réelle déclarée des fichiers de poids", "base_bytes": 932857760, "estimated_bytes": 1212715088, "overhead": 0.3}}, "quantization": {"available": true, "variants": [{"label": "Q8_0", "filename": "DeepSeek-V4-Flash-MTP-Q4K-Q8_0-F32.gguf", "size": 3807602400, "size_human": "3.5 Go", "memory_bytes": 4949883120, "memory_human": "4.6 Go", "note": "Pratiquement sans perte perceptible.", "rank": 30, "memory_gb": 4.6, "state": "tient", "verdict": "Tient dans la mémoire déclarée"}, {"label": "variante", "filename": "DeepSeek-V4-Flash-DSpark-support-0731.gguf", "size": 5989114272, "size_human": "5.6 Go", "memory_bytes": 7785848553, "memory_human": "7.3 Go", "note": "", "rank": 34, "memory_gb": 7.3, "state": "juste", "verdict": "Tout juste : marge très faible"}], "recommended": {"label": "variante", "filename": "DeepSeek-V4-Flash-DSpark-support-0731.gguf", "size": 5989114272, "size_human": "5.6 Go", "memory_bytes": 7785848553, "memory_human": "7.3 Go", "note": "", "rank": 34, "memory_gb": 7.3, "state": "juste", "verdict": "Tout juste : marge très faible"}, "lightest": {"label": "Q8_0", "filename": "DeepSeek-V4-Flash-MTP-Q4K-Q8_0-F32.gguf", "size": 3807602400, "size_human": "3.5 Go", "memory_bytes": 4949883120, "memory_human": "4.6 Go", "note": "Pratiquement sans perte perceptible.", "rank": 30, "memory_gb": 4.6, "state": "tient", "verdict": "Tient dans la mémoire déclarée"}, "memory_gb": 8.0, "disk_gb": 20.0, "fitting_count": 2, "overhead": 0.3, "note": "Tailles issues des fichiers déclarés par le producteur, majorées de 30% pour l’exécution. Une variante plus compressée consomme moins de mémoire et dégrade les réponses : cette dégradation n’est pas mesurée ici."}, "editorial_quality_score": null, "editorial_quality_blockers": []}