Qwen3.8 27B Swift-1.5-Uncensored

User reports a 2.3bpw fusion of swift-1.5-uncensored and mirai's 2.5bpw model running on RTX 3080/3080 Ti cards at 65-70 t/s with MTP on evals. Setup is LlamAmpere with 4/4 KV cache, 12GB VRAM, and MTP enabled. The model retained 85% of BF16 performance on LiveCodeBench across 7 runs on 3060/3080/3080 Ti cards. The user notes the model is usable for standard agentic tasks and subjectively places it between BF16 versions of Qwen3.5 and Qwen3.6. The 3/3 and 3/2 KV cache variants support 205K and 230K context respectively at 11GB VRAM.