Benchmark result
ggml-org/gpt-oss-20b-GGUF on AMD Radeon RX 9070/9070 XT/9070 GRE — 143.1 tok/s
Measured with llama.cpp b11388-050439614 on October 5, 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
2nd fastest of 3 runs of this model on AMD Radeon RX 9070/9070 XT/9070 GRE · median 143.1 tok/s.
sort
- 1144.0tok/s67.9llama.cpp
- 2143.1tok/s73.0llama.cppthis run
- 3139.3tok/s73.2llama.cpp
ggml-org/gpt-oss-20b-GGUF on other hardware
Reproduce this run
toolllama.cpp b11388-050439614
modelggml-org/gpt-oss-20b-GGUF
context32,768
effortmedium (model default)
think limitnone
samplingtemperature 1 · top_p 1 · top_k 0 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.87+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "ggml-org/gpt-oss-20b-GGUF" --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.