ComfyUI v0.45.0 roughly doubles Qwen3.x local text generation speed
Overview
ComfyUI says its v0.45.0 update roughly doubles Qwen3.x token generation speed on the same hardware and checkpoints, without changing model quality.
In ComfyUI's own benchmarks on an RTX 5090, Qwen3.5 9B rose from 106 to 219 tokens per second, and Qwen3.8 27B describing a 1536×1536 image rose from 55 to 122. The company attributes the gains to a rewritten linear kernel, adaptive tree multi-token prediction, and a new attention path.
According to the same post, the improvements run on NVIDIA and AMD GPUs under Windows and Linux and need no extra setup beyond updating to ComfyUI v0.45.0.
Written by AI from the articles below · updated Nov 11, 7:32 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Comfy BlogOfficialPickComfyUI v0.45.0 doubles Qwen3.x local text generation speed
AIComfyUI says its v0.45.0 update roughly doubles Qwen3.x token generation speed on the same hardware and checkpoints, without changing model quality. On an RTX 5090, Qwen3.5 9B rose from 106 to 219 tokens per second, and Qwen3.8 27B describing a 1536×1536 image rose from 55 to 122. The gains come from a rewritten linear kernel, adaptive tree multi-token prediction, and a new attention path, and the post says they run on NVIDIA and AMD without extra setup.
Heat Trend
- Current comparable heat
- 6
- Peak comparable heat
- 10Nov 11, 1:00 PM ET
- Change in past 24 hours
- –
The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.