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-Qwen2.5-0.5BMistral-Small-3.1-DRAFT-0.5BQwen3.8-27B-DSpark-drafterpythia-14m-dd-rus-draftDeepSeek-R1-DRAFT-Qwen2.5-0.5B-GGUFrevonance-drafter-qwen2.5-0.5brevonance-drafter-smollm2-360mQwenPhi-4-0.5b-Draft-mlx-fp16revonance-drafter-tinyllama-1.1bDeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-GGUFllama2-7B-drafter-initQwen3-8B-Ins-Draft-OPDDeepSeek-R1-DRAFT-Qwen2.5-0.5B-GGUFMistral-Small-3.1-DRAFT-0.5B-GGUForbit-drafter-qwen2.5-0.5borbit-drafter-smollm2-360mcheckpoint-draft-dflash2orbit-drafter-tinyllama-1.1bMistral-Small-3.1-DRAFT-0.5B-mlx-4BitMistral-Small-3.1-DRAFT-0.5B-Q4_K_M-GGUFDeepSeek-R1-DRAFT-Qwen2.5-0.5B-q3-mlxDeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-mlx-8BitDSpark-Gemma-4-31B-draftQwQ-32B-DRAFT-0.5B-GGUFllamagen_drafterDeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-Q8-mlxDeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5BDeepSeek-R1-DRAFT-Qwen2.5-Coder-0.5B-Q4-mlxDeepSeek-R1-DRAFT-Qwen2.5-0.5B-Q4_K_M-GGUFDeepSeek-R1-DRAFT-Qwen2.5-0.5B-q4-mlx
