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.
BitCPM-CANN-3BBitCPM-CANN-3B-unquantizedFLUX.2-Klein-4B-3bitQwen3.8-9B-mlx-3Bitqwen2.5-coder-32b-bitnet-1.58bbitnet_b1_58-3B-i1-GGUF16_bit_kmap_gguf_3epoch_2k_kmap_queen3BGLM-4.5-Air-3bitLlama-3.3-70B-Instruct-3bitMistral-Small-4-119B-2603-Mixed-3bit-MLXJosiefied-Qwen2.5-3B-Instruct-abliterated-v1-4-bitQwen3.8-2.4T-A95B-3bit-UVMAXBitnet-Llama3-from8BM-now2B-GGUFQwen3.6-27B-V2-abliterated-uncensored-6-bit-mlxbitnet_b1_58-3B-GGUFLlama-3-with-Bitext-27k-GGUFLongCat-2.0-3bitgemma-4-26B-A4B-it-uncensored-abliterix-MLX-3bit-int3-affineLongCat-2.0-3bit-UVMAXgranite-4.2-8b-3bit-mlxKimi-K2-Instruct-0905-MLX-3bitQwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-MLX-3bitBitCPM-CANN-3B-ggufgranite-4.2-30b-3bit-mlxQwen3.6-35B-A3B-3bit-MLXHuihui-Qwen3-Next-80B-A3B-Instruct-abliterated-mlx-3BitBitnet-LLaMa3-GGUFQwen3.6-35B-A3B-uncensored-abliterix-v2-MLX-3bit-mixed_3_6granite-4.2-3b-3bit-mlxQwen3.8-27B-3bit-mlx
