Qwen3.8-27B-GSQ-RCO-MLX

An Apple Silicon MLX package of the mixed-IQ GSQ-RCO Qwen3.8-27B checkpoint. The original GGUF quantized tensor payloads are preserved losslessly inside a packed Safetensors file. This is a **custom packed format**, not a standard `mlx-lm` checkpoint. Load it with the separate `mlx-GSQ-RCO` runtime. The weights use 11 quantized types: `IQ1_M`, `IQ1_S`, `IQ2_XXS`, `IQ2_XS`, `IQ2_S`, `IQ3_XXS`, `IQ3_S`, `IQ4_XS`, `Q2_K`, `Q4_K`, and `Q6_K`. Plain F32 and BF16 tensors are also present. The GGUF-to-Safetensors converter verifies all 866 source payloads by SHA-256. On an Apple M3 Pro, the runtime measured 22.3 tok/s prefill for a 182-token prompt and 9.14 tok/s for 64-token decode. A 256-token generation run used about 10.3 GB peak unified memory. The half4-vectorized tiled QMM kernel improved large single-layer QMM throughput by 2.6–3.2x versus the earlier scalar GEMM version; end-to-end prefill improved from 10.5 to 22.3 tok/s in the recorded run. Results vary by machine, prompt, and software versions. More benchmark context is in the GitHub README.

번역 준비 중입니다. 원문을 표시합니다.