Benchmark result
Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M on NVIDIA GeForce RTX 2080 Ti — 56.5 tok/s
Measured with llama.cpp b11671-ba3c05f71 on October 16, 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 2080 Ti · median 61.0 tok/s.
sort
- 170.0tok/s50.9llama.cpp · Q4_K_M
- 261.0tok/s52.2llama.cpp · Q4_K_M
- 356.5tok/s54.6llama.cpp · Q4_K_Mthis run
Reproduce this run
toolllama.cpp b11671-ba3c05f71
modelAldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M (Q4_K_M)
context16,384
thinkingoff
samplingtemperature 0.800000011920929 · top_p 0.949999988079071 · top_k 40 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.96+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Aldaris/Qwen3-8B-Q4_K_M-GGUF:Q4_K_M" --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.