Tag
An open-source stack using Qwen2.5-32B-Instruct with longctx and vllm-turboquant on a single AMD MI300X achieves competitive results (0.601-0.688) versus SubQ's closed model (0.659) on the MRCR v2 1M-context benchmark, demonstrating open-weights approaches are within striking distance.
The author reports successful experiments running MRCR v2 with 1M context length on a single MI300X using Qwen2.5-32B and FAISS, achieving competitive scores at low cost.