Qwen 3.8 27B running on 4x 3090s in Opencode.
Eight parallel agents can run at this speed with no slowdown and it also does vision.
Qwen 3.8 Flash Next running on my laptop, in opencode, with 8GB VRAM + 64GB RAM
Qwen 3.8 Flash Next 4x3090.
Mike drop.
Qwen 3.8 Flash Next
Vision enabled, still going strong :) It's FAST. 9s - Image description 3m09s - 3d Visualisation Take a tour :) 4x3090, VLLM, 256k ctx Average: ~100t/s albucino/Qwen3.8-Flash-Next-W4A16-FP8PLE
You have reached the end of the archive
All of qwen38