Benchmark result
gpt-oss-20b-UD-Q6_K_XL on 2× NVIDIA GeForce RTX 5060 — 179.0 tok/s
Measured with llama.cpp b10851-67672dc5b on September 8, 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.
How this run compares
1st fastest of 3 runs of this model on 2× NVIDIA GeForce RTX 5060 · Multi-GPU · median 123.5 tok/s.
sort
- 1179.0tok/s70.4llama.cpp · Q6_Kthis run
- 2123.5tok/s77.5llama.cpp · Q6_K
- 3100.6tok/s71.9llama.cpp · Q6_K
Reproduce this run
toolllama.cpp b10851-67672dc5b
modelgpt-oss-20b-UD-Q6_K_XL (Q6_K)
context131,072
thinkingon
samplingtemperature 0.20000000298023224 · top_p 0.8999999761581421 · top_k 0 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.55+97
Set those in llama.cpp, then:
llm-benchmark benchmark --model "gpt-oss-20b-UD-Q6_K_XL" --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.