Benchmark result
mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M on NVIDIA GeForce RTX 4070 — 63.9 tok/s
Measured with llama.cpp manual on October 12, 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 NVIDIA GeForce RTX 4070 · median 63.9 tok/s.
sort
- 168.2tok/s73.8llama.cpp · Q4_K_M
- 263.9tok/s71.8llama.cpp · Q4_K_Mthis run
- 356.3tok/s69.2llama.cpp · Q4_K_M
Reproduce this run
toolllama.cpp manual
modelmistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_K_M (Q4_K_M)
context65,536
think limitnone
clientv0.4.92+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "mistralai/Ministral-3-8B-Instruct-2512-GGUF:Q4_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.