Benchmark result
muse-glimmer:30b-q4_K_M on 2× AMD Radeon RX 7800 XT — 26.7 tok/s
Measured with Ollama 0.40.5 on October 16, 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
3rd fastest of 4 runs of this model on 2× AMD Radeon RX 7800 XT · Multi-GPU · median 27.5 tok/s.
sort
- 128.4tok/s82.9Ollama · Q4_K_M
- 228.4tok/s78.8Ollama · Q4_K_M
- 326.7tok/s83.6Ollama · Q4_K_Mthis run
- 426.6tok/s82.7Ollama · Q4_K_M
Reproduce this run
toolOllama 0.40.5
modelmuse-glimmer:30b-q4_K_M (Q4_K_M)
context65,536
thinkingon
effortmedium
samplingtemperature 1 · top_p 0.95 · top_k 64
clientv0.4.89+102
Set those in Ollama, then:
llm-benchmark benchmark --model "muse-glimmer:30b-q4_K_M" --tool "Ollama"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.