Benchmark result
qwen3.8-27b-turbo-fable-cold-fusion-735-882-heretic-uncensored-mtp-nm-dau-nvfp4-highest on NVIDIA GeForce RTX 5090 — 56.5 tok/s
Measured with LM Studio on September 9, 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
toolLM Studio
modelqwen3.8-27b-turbo-fable-cold-fusion-735-882-heretic-uncensored-mtp-nm-dau-nvfp4-highest
context65,536
thinkingoff
clientv0.4.58+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen3.8-27b-turbo-fable-cold-fusion-735-882-heretic-uncensored-mtp-nm-dau-nvfp4-highest" --tool "LM Studio"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.