Benchmark result
peculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF on NVIDIA GeForce RTX 4070 — 95.5 tok/s
Measured with Unsloth Studio on October 7, 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
1st fastest of 3 runs of this model on NVIDIA GeForce RTX 4070 · median 90.9 tok/s.
sort
- 195.5tok/s71.6Unsloth Studio · Q6_K_XL · KV q8_0this run
- 290.9tok/s71.3Unsloth Studio · Q6_K_XL · KV q4_0
- 387.2tok/s65.9Unsloth Studio · Q6_K_XL · KV q4_0
Reproduce this run
toolUnsloth Studio
modelpeculiar-ragdoll/Sharp-Spark-X2.5-4B-GGUF (Q6_K_XL)
context65,536
kv cacheq8_0
thinkingon
think limitnone
samplingtemperature 0.7 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.89+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "peculiar-ragdoll/Sharp-Spark-X2.5-4B-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.