Gufo-Qwen3.6-35B-A3B-Q6dense – 3095tok/s prefill; 190 tok/s decode on Strix Halo
Description and use
Gufo-Qwen3.6-35B-A3B-Q6dense delivers fast prefill (3095 tokens/s) and decode (190 tokens/s) performance on the Strix Halo GPU, making it suitable for prototyping and internal workflows. Adoption requires manual inspection of compatibility, as integration signals are sparse. With license, maintenance, and update checks, the project is considered production‑ready for medium‑risk environments.
Use in a workflow
Gufo-Qwen3.6-35B-A3B-Q6dense – 3095tok/s prefill; 190 tok/s decode on Strix Halo may be useful when its README and activity match a concrete workflow.
Limitations and review notes
Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.
- Source: hackernews
- Record date: 2026-10-03T06:26:41.000Z