Benchmark result
allenai.OLMoE-1B-7B-0125-Instruct.Q5_K_M on NVIDIA GeForce RTX 4060 Laptop GPU — 186.7 tok/s
Measured with llama.cpp b11985-6d194531e on October 30, 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 10 runs of this model on NVIDIA GeForce RTX 4060 Laptop GPU · median 185.3 tok/s.
sort
- 1188.7tok/s30.1llama.cpp · Q5_K_M
- 2186.7tok/s29.6llama.cpp · Q5_K_Mthis run
- 3186.6tok/s35.5llama.cpp · Q5_K_M
- 4186.5tok/s24.2llama.cpp · Q5_K_M
- 5185.5tok/s37.2llama.cpp · Q5_K_M
- 6185.1tok/s29.7llama.cpp · Q5_K_M
- 7184.9tok/s32.2llama.cpp · Q5_K_M
- 8183.3tok/s39.6llama.cpp · Q5_K_M
- 9182.0tok/s28.8llama.cpp · Q5_K_M
- 10181.6tok/s26.7llama.cpp · Q5_K_M
Reproduce this run
toolllama.cpp b11985-6d194531e
modelallenai.OLMoE-1B-7B-0125-Instruct.Q5_K_M (Q5_K_M)
context32,768
think limitnone
samplingtemperature 0.800000011920929 · top_p 0.949999988079071 · top_k 40 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.98+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "allenai.OLMoE-1B-7B-0125-Instruct.Q5_K_M" --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.