qwen38-27b-exl3-rdna4
Luke458/qwen38-27b-exl3-rdna4
Python
Qwen3.8-27B EXL3 on AMD gfx1201: RX 9070 XT (16 GB, tested) and Radeon AI PRO R9700 (32 GB). vLLM plugin with custom kernels: ~80 tok/s with MTP speculative decoding, int8 KV cache, 32k-64k context on 16 GB (up to 262k on 32 GB), vision and tool calls.