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 a Single RTX 4090(3 posts)→
More from coding & agent
- Perplexity open-sources SPACE sandbox; 108 escape attempts by frontier models all failed — perplexity_ai · 2026-10-16
- Blackstone goes all-in on Factory for autonomous software development — matanSF · 2026-10-16
- AI software factories hinge on the Factory Loop, not faster code generation — Pavan_Belagatti · 2026-10-16
- 'Dropping a 3,000-line PR twenty minutes after ticket assignment' — AI coding meme goes viral — facontidavide · 2026-10-16
- Self Labs launches Agent Vault to let AI agents log in and pay with credit cards — EXM7777 · 2026-10-16
- Plane Agents: triggers, not prompts, are what turn chatbots into workflow agents — JosephJacks_ · 2026-10-16