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.
qgallouedec_gemma-3-27b-it-codeforces-SFT-GGUFgpt2-qgtinyllama-1.1b-qgllama3.2-3b-qgqwen2.5-1.5b-qgphi3.5-mini-qgtiny-Qwen2ForCausalLM-2.5tiny-FalconMambaForCausalLMBioMistral-7B-AWQ-QGS128-W4-GEMMLlamma-3_QG_V.2.0BioMistral-7B-DARE-AWQ-QGS128-W4-GEMMgemma-3-12b-it-heretic-mlx-bf16-affine-qgroup32-q8Qwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-affine-qgroup32-q5qmst-qggt5-french-qgQwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-affine-qgroup32-q4gemma-3-12b-it-norm-preserved-biprojected-abliterated-mlx-bf16-affine-qgroup32-q8Qgis-Hermes-3-Llama-3.2-3BQwen-2.5-7B-Simple-RLptt5-ptbr-qgtiny-GPTNeoXForCausalLMNemoMix-Unleashed-12B-mlx-bf16-mxfp4-qgroup32-mixed_4_6ScaleQuest-DeepSeekMath-7B-QGenHuihui-Ling-mini-2.0-abliterated-mlx-bf16-mxfp4-qgroup32-mixed_4_6online-dpo-qwen2-2Qwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-affine-qgroup32-q6BioMistral-7B-AWQ-QGS128-W4-GEMVtiny-Qwen2ForCausalLM-CoderQwen2.5-14B-Instruct-1M-abliterated-mlx-bf16-affine-qgroup32-q8BioMistral-7B-SLERP-AWQ-QGS128-W4-GEMM
