Qwen3.8 27B
on NVIDIA RTX 4090 · llama.cpp · 196,608 ctx
Oct 3, 2026
Use cases
coding
Summary
User reports Qwen3.8-27B at 115 t/s decode on a single RTX 4090 24 GB.
Setup is llama.cpp b11115 with llama-swap v257, IQ4_XS GGUF quant, q8_0 KV cache, 196608 context, and draft-MTP speculative decoding.
The user notes the DeepSWE result is a single task, not an average, and that the model passed 40/43 hidden tests and kept 109/109 existing tests.