Qwen3.8 27B
on NVIDIA RTX 3090 · llama.cpp · 240,000 ctx
Sep 15, 2026
Use cases
codingagentic
Summary
User reports Qwen3.8 27B at 90+ t/s on an RTX 3090 through 100K tokens, with context up to 240K.
Setup is a custom llama.cpp fork (llamAmpere) optimized for Ampere, using the IQ4_XS-M GGUF quant at temperature 1.
The user claims 80% faster than the nearest competitor at 200K context and says it runs faster than API speeds.