Benchmark result
unsloth/Qwen3.5-0.8B-MTP-GGUF:Q8_K_XL on NVIDIA GeForce RTX 4070 — 198.4 tok/s
Measured with llama.cpp manual on October 13, 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.
Reproduce this run
toolllama.cpp manual
modelunsloth/Qwen3.5-0.8B-MTP-GGUF:Q8_K_XL (Q8_K)
context262,144
thinkingon
think limitnone
clientv0.4.92+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "unsloth/Qwen3.5-0.8B-MTP-GGUF:Q8_K_XL" --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.