models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
DeepSeek-R1-DRAFT-Qwen2.5-0.5Balamios_Mistral-Small-3.1-DRAFT-0.5B-GGUFQwen3.8-Flash-Next-MTP-Drafter-GGUFMistral-Small-3.1-DRAFT-0.5BQwen3.8-27B-DSpark-drafterMiMo-V2.5-Pro-DFlash-draft-ik-llama-GGUFqwen3-0.6b-devin-draftLFM2.5-VL-3B-DFlash-drafteralamios.Mistral-Small-3.1-DRAFT-0.5B-GGUFQwen2.5-Coder-0.5B-QwQ-draft-GGUFpythia-14m-dd-rus-draftDeepSeek-R1-DRAFT-Qwen2.5-0.5B-GGUFPJMixers-Dev-Qwen2.5-QwQ-RP-Draft-v0.1-0.5B-GGUFcheckpoint-draft-dflash2DeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-GGUFQwenPhi-4-0.5b-Draft-mlx-fp16llama2-7B-drafter-initTokForge-AccelerationPack-DraftOrnith-1.0-397B-IQ2_KS-DFlash-Drafter-GGUFMistral-Small-3.1-DRAFT-0.5B-MLX-4bitQwen3.8-Flash-Next-MTP-DRAFT-HEAD-ROCMFP4-GGUFQwen3-8B-Ins-Draft-OPDdrafter-wmt16-translate-fiendrafter-wmt16-translate-ruendrafter-wmt16-translate-trenMistral-Small-3.1-DRAFT-0.5B-GGUFdrafter-wmt16-translate-csendrafter-wmt16-translate-deenOrnith-1.5-397B-IQ2_XXS-DFlash-Drafter-GGUFMistral-Small-3.1-DRAFT-0.5B-mlx-4Bit