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)→
More from coding & agent
- Grok Bot Enhances Agent Trust with Mobile Approval Workflow — XFreeze · 2026-08-25
- Integrating FetchSandbox MCP cuts agent verification costs — Common_Dream9420 · 2026-08-25
- ComfyUI Universal Media Loader: one node for loading, cropping and masking — 3deal · 2026-08-25
- Real-time configuration modification with OMP — KingBootoshi · 2026-08-25
- Building a Custom Obsidian Search with Claude Code in Five Minutes — evielync · 2026-08-25
- Shared MCP space for agents to draw together — Poowatereater · 2026-08-25