Benchmark result
Muse-Glimmer-30B-KQuant-17GB-Q4_K_M — 65.7 tok/s
Measured with llama.cpp b12626-b05204927 on November 22, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
Muse-Glimmer-30B-KQuant-17GB-Q4_K_M on other hardware
- 66.0tok/s85.4Unknown hardware · Q4_K_M
- 65.7tok/s82.1Unknown hardware · Q4_K_Mthis run
Reproduce this run
toolllama.cpp b12626-b05204927
modelMuse-Glimmer-30B-KQuant-17GB-Q4_K_M (Q4_K_M)
context131,072
think limitnone
samplingtemperature 0.800000011920929 · top_p 0.949999988079071 · top_k 40 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.99+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Muse-Glimmer-30B-KQuant-17GB-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.