Qwen3.x
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- ComfyUI v0.45.0 Boosts Qwen3.x Token Generation
Comfy says it rewrote ComfyUI’s local text-generation path for Qwen3.x, enabling token generation up to twice as fast without changing the models or output quality. It reports that Qwen3.5 9B rose from 106 to 219 tokens per second on an RTX 5090, while Qwen3.8 27B rose from 55 to 122 tokens per second for 1536×1536 image descriptions. The improvements are available in ComfyUI v0.45.0, but the performance figures have not been independently verified.
Comfy Blog · 🔥 0
Experience and discussion from the community
Share my Qwen3.x experienceAsk about Qwen3.x
Nobody has shared their experience with Qwen3.x yet.