Benchmark result
peculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF on NVIDIA GeForce RTX 4070 — 134.6 tok/s
Measured with Unsloth Studio on October 14, 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
5th fastest of 5 runs of this model on NVIDIA GeForce RTX 4070 · median 137.9 tok/s.
sort
- 1143.3tok/s52.6Unsloth Studio · Q6_K_XL · KV f16
- 2141.3tok/s57.4Unsloth Studio · Q6_K_XL · KV q8_0
- 3137.9tok/s50.5Unsloth Studio · Q6_K_XL · KV q4_0
- 4136.3tok/s57.0Unsloth Studio · Q6_K_XL · KV q8_0
- 5134.6tok/s57.1Unsloth Studio · Q6_K_XL · KV q8_0this run
Reproduce this run
toolUnsloth Studio
modelpeculiar-ragdoll/Sharp-MiniCPM5-2B-GGUF (Q6_K_XL)
context131,072
kv cacheq8_0
thinkingon
think limitnone
samplingtemperature 0.7 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.93+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "peculiar-ragdoll/Sharp-MiniCPM5-2B-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.