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.
qwen14b-code-trainer-v9_mixedFuseO1-DeepSeekR1-Qwen2.5-Coder-14B-Preview-mixed_3_6Qwen3-Coder-Next-mixed-mxfp4-bf16Qwen3-Coder-Next-MixedCode-Prune70-BF16Qwen3-Coder-30B-A3B-Instruct-W4A16-mixed-AWQseccodeplt-qwen2.5-coder-3b-fixed-mixed-grpo-alpha-0.5-pi-theta-real-detector-reward-v3seccodeplt-qwen2.5-coder-7b-fixed-mixed-grpo-alpha-0.5-pi-theta-real-detector-reward-v3Qwen3-Coder-Next-int2-mixed-AutoRoundseccodeplt-qwen2.5-coder-7b-fixed-mixed-grpo-alpha-0.5-pi-theta-real-reward-v2Seed-Coder-8B-Base-MLX-mixed-3-4Qwen3-Coder-30B-A3B-Instruct-int4-mixed-AutoRoundGoedel-Code-Prover-8B-mlx-group_size64-quant_predicate_mixed_4_6seccodeplt-qwen2.5-coder-3b-fixed-mixed-grpo-alpha-0.5-pi-theta-real-reward-v2Kleiner-Coder-35B-mixed-q2kQwen3-Coder-Next-int4-mixed-AutoRoundCode-Writer-V2-Obliterated-AWQ-Mixed-Leandeepseek-coder-1.3b-instruct-mixed_fp4deepseek-coder-1.3b-instruct-mixed_fp8qwen14b-code-trainer-v8_mixedDeepSeek-Coder-1.3b-base-AQLM-2bit-mixed-1x14all_mixed_full_sft_qwen3_coder_30b_a3b_instructllama3-code-mixed-loraCodeLlama-34b-hf-AQLM-2bit-mixed-1x15tora-code-7b-mixed-regex-patterns-v1.0bDeepSeek-Coder-6.7b-base-AQLM-3bit-mixed-2x12DeepSeek-Coder-6.7b-base-AQLM-4bit-mixed-2x15DeepSeek-Coder-33b-base-AQLM-2bit-mixed-1x15DeepSeek-Coder-1.3b-base-AQLM-2bit-mixed-finetuned-1x14FL_1000_NL_Code_gemma-2-9b-it-star-mixed_direct-OP-final_v2_10-2-3Rounds-iter-3qwen14b-code-trainer-v7_mixed