Benchmark result
unsloth/Qwen3.5-4B-MTP-GGUF on NVIDIA GeForce RTX 4070 — 121.1 tok/s
Measured with Unsloth Studio on September 27, 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.
How this run compares
3rd fastest of 4 runs of this model on NVIDIA GeForce RTX 4070 · median 122.0 tok/s.
sort
- 1146.2tok/s70.1Unsloth Studio · UD-Q4_K_XL · KV f16
- 2123.0tok/s53.8Unsloth Studio · KV f16
- 3121.1tok/s57.6Unsloth Studio · UD-Q4_K_XL · KV f16this run
- 425.5tok/s58.1Unsloth Studio · UD-Q6_K_XL · KV f16
Reproduce this run
toolUnsloth Studio
modelunsloth/Qwen3.5-4B-MTP-GGUF (UD-Q4_K_XL)
context65,536
kv cachef16
samplingtemperature 0.7 · top_p 0.8 · top_k 20 · min_p 0 · presence_penalty 1.5
clientv0.4.80+98
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "unsloth/Qwen3.5-4B-MTP-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.