Qwen 3.8 27b Local Coding Test: 73 tok/s at 128k Context, Usable Performance
julianharris · x · 2026-08-17
A developer tests Qwen 3.8 27b for local coding. With 4-bit unsloth quant on RTX 4090, it achieves 73 tok/s at 128k context, absolutely usable. Disabling thinking mode gives 78 tok/s but much lower quality. Compared to Qwen 3.6 in May, setup is much simpler. Local AI coding agents look promising.
Related event: Qwen3.8-27B local benchmarks: from RTX 4080 Super to RTX 6000 Pro(7 posts)→
More from coding & agent
- Six-month prediction: hiring for generic agent harnesses built from scratch will cool — yi111 · 2026-10-16
- Omarchy ISO wouldn't boot on NVIDIA, so he had Claude patch it — indragie · 2026-10-16
- Dev uses Grok to clean up 3D printer firmware, catches it sneaking in nonsense code — yacineMTB · 2026-10-16
- A rude AI agent took 89% of a shared resource in 102-run multi-agent personality experiment — Brave-History-6502 · 2026-10-16
- Guardrails can make risky delegation work — but it takes a full-time team, says iandanforth — iandanforth · 2026-10-16
- What can you truly delegate? Only tasks with unambiguous, verifiable results — iandanforth · 2026-10-16