Benchmark result
openbmb/MiniCPM5-1B-GGUF on Intel(R) Arc(TM) 140V GPU (16GB) — 63.5 tok/s
Measured with Unsloth Studio on September 21, 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 2 runs of this model on Intel(R) Arc(TM) 140V GPU (16GB) · median 74.5 tok/s.
sort
- 185.6tok/s13.8Unsloth Studio
- 263.5tok/s15.7Unsloth Studiothis run
openbmb/MiniCPM5-1B-GGUF on other hardware
Reproduce this run
toolUnsloth Studio
modelopenbmb/MiniCPM5-1B-GGUF
context8,192
clientv0.4.71+98
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "openbmb/MiniCPM5-1B-GGUF" --tool "Unsloth 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.