Model benchmarks
muse-glimmer:latest local LLM performance
As of August 2026, muse-glimmer:latest runs at up to 34.8 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
OllamaQ4_K_M
Model size
27.9B
Peak speed
34.8 tok/s
Average speed
34.8 tok/s
Min memory
15.5 GB
Max context
8,231 tokens
Best quality
93.1
Benchmark runs
2
GPUs tested
1
Performance by hardware and tool
Every hardware/tool/quantization combination muse-glimmer:latest has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon RX 7900 XTX | Ollama | Q4_K_M | 34.8 tok/s | 34.8 tok/s | 15.5 GB | 8,231 tokens | 83.3 | 2 |
Frequently asked questions
- How fast is muse-glimmer:latest for local inference?
- Across 2 community benchmark runs, muse-glimmer:latest reaches up to 34.8 tok/s and averages 34.8 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
- How much memory does muse-glimmer:latest need?
- The leanest observed configuration used about 15.5 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run muse-glimmer:latest?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.