MiniCPM5-2B-MLX-8bit
MLX 8-bit conversion of OpenBMB/MiniCPM5-2B, a 2B dense Llama-based model for local deployment, coding, reasoning, long-context work, and...
MLX 8-bit conversion of OpenBMB/MiniCPM5-2B, a 2B dense Llama-based model for local deployment, coding, reasoning, long-context work, and...
MLX 4-bit build of jica98/qwen3.5-4B-super-coder. The source repo only ships the LoRA adapter and GGUF exports, so this...
Это квантование лишает модель визуальной башни и сохраняет только текстово-текстовые возможности. Для версии с поддержкой зрения проверьте lukaskremla/Qwen3.8-27B-4bit-MLX....
This is the text-only, lossless-weight MLX-LM conversion of N8Programs/Qwen3.6-35B-A3B-AntiLoop-NVFP4. It deliberately omits the vision tower so the mixed...
— Source revision: effaeda477c041c107d5a3d8c599cb5d6c5878ef — Architecture: Cohere2MoeForCausalLM / cohere2moe — Quantization: MLX mxfp4`, group size 32, 4 bits...
MLX conversion of OBLITERATUS/Qwen3.6-27B-OBLITERATED for Apple Silicon. The model uses an alternating linear/full attention pattern across 64 layers...
This is an MLX release of an abliterated, uncensored version of Qwen’s Qwen3.6-27B with the source image/video payload...
This repo is a straight MLX oQ8 quant of kai-os/Carnice-27b for local Apple Silicon inference. No other edits,...
Uncensored Llama 3.3 70B on Apple Silicon, at 8-bit for maximum fidelity. Abliterated and converted to MLX —...
Summary. This is a non-quantized MLX conversion of gpt-oss-120B in bfloat16 (bf16). Built for Apple Silicon with Metal...