User floored by local Qwen 3.8 27B performance, achieving 100 tok/s on RTX 4090

mayfer · x · 2026-08-25

A user tested Qwen 3.8 27B Q4 locally on an RTX 4090 (achieving 100 tok/s with MTP) and was floored by the results. Assigning a complex Rust project task (with GUI) typically suited for Sol or Opus, the model compacted the context twice and delivered a working result, exceeding expectations.

Related event: Qwen 3.8 27B Hits 100 tok/s on RTX 4090, Rivaling Claude 3 Opus(2 posts)→

Original post →

More from coding & agent

coding & agent channel →