Benchmark result
bartowski/Qwen3.8-27B-GGUF/Qwen3.8-27B-IQ4_XS on NVIDIA GeForce RTX 4090 +1 more — 42.1 tok/s
Measured with atomic-chat manual on November 1, 2026.
What the model built
Open full screen →The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.
Reproduce this run
toolatomic-chat manual
modelbartowski/Qwen3.8-27B-GGUF/Qwen3.8-27B-IQ4_XS
context256,000
clientv0.4.98+102
Set those in atomic-chat, then:
llm-benchmark benchmark --model "bartowski/Qwen3.8-27B-GGUF/Qwen3.8-27B-IQ4_XS" --tool "atomic-chat"The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.