Benchmark result
IFM/K2-Horizon-7B-GGUF on NVIDIA GeForce RTX 4070 — 68.1 tok/s
Measured with Unsloth Studio on October 15, 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
3rd fastest of 3 runs of this model on NVIDIA GeForce RTX 4070 · median 68.5 tok/s.
sort
- 171.9tok/s66.0Unsloth Studio · Q4_K_M · KV q4_0
- 268.5tok/s67.5Unsloth Studio · Q4_K_M · KV q4_0
- 368.1tok/s70.9Unsloth Studio · Q4_K_M · KV q4_0this run
Reproduce this run
toolUnsloth Studio
modelIFM/K2-Horizon-7B-GGUF (Q4_K_M)
context65,536
kv cacheq4_0
thinkingon
effortlow
think limitnone
samplingtemperature 0.7 · top_p 0.95 · top_k -1 · min_p 0.01 · presence_penalty 0
clientv0.4.96+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "IFM/K2-Horizon-7B-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.