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.
cs2881r-hw1Huihui-Qwen3-Next-80B-A3B-Thinking-abliterated-mlx-8Bitzagreus-0.4B-italic-extkdzagreus-0.4B-italic-softkdHuihui-Qwen3-Next-80B-A3B-Thinking-abliterated-mlx-4BitHuihui-GLM-4.7-Flash-abliterated-mlx-8BitGLM-4.7-PRISM-Q8_0-GGUFDeepSeek-V3.2_dq4-mlxHuihui-Qwen3-30B-A3B-Instruct-2507-abliterated-mlx-6Bit-gs32Huihui-GLM-4.7-Flash-abliterated-Q8_0-GGUFGLM-5-abliterated-dq4-mlxGLM-5.1-FP8_dq4-mlxGLM-4.7-PRISM-Q6_K-GGUFGLM-4.7-PRISM-TQ2_0-GGUFGLM-5-abliterated-dq3-mlxHuihui-GLM-4.7-Flash-abliterated-Q6_K-GGUFQwen2.5-QwQ-37B-Eureka-Triple-Cubed-abliterated-uncensored-mlx-6Bit-gs32GLM-4.7-PRISM-mlx-6BitGLM-4.7-PRISM-Q2_K-GGUFHuihui-Qwen3-30B-A3B-Thinking-2507-abliterated-mlx-6Bit-gs32GLM-4.6-mlx-6BitMiniMax-M2.5_dq4-mlxreappraisal-4b-grpo-committeetinysql_interp_bm1_cs2_experiment_2.10countdown_sftGLM-5_dq3-mlxtinysql_interp_bm2_cs2_experiment_5.2cs224r-finalproj-checkpoint1-sftcs2200-llama-3.2-1B-instruct-no-custom-trainercs224r_project_qwen_dpo_instruct
