Benchmark result
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-IQ3_S on NVIDIA GeForce RTX 5070 Ti — 49.0 tok/s
Measured with llama.cpp b1-2168b0c on September 15, 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.
How this run compares
2nd fastest of 4 runs of this model on NVIDIA GeForce RTX 5070 Ti · median 48.7 tok/s.
sort
- 149.5tok/s85.6llama.cpp
- 249.0tok/s70.9llama.cppthis run
- 348.4tok/s85.5llama.cpp
- 447.5tok/s87.1llama.cpp
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-IQ3_S on other hardware
Reproduce this run
toolllama.cpp b1-2168b0c
modelISTA-DASLab/Qwen3.8-27B-GSQ-RCO-IQ3_S
context32,768
effortxhigh (model default)
samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.59+97
Set those in llama.cpp, then:
llm-benchmark benchmark --model "ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-IQ3_S" --tool "llama.cpp"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.