LLM Inference Benchmark Explorer
Muse-Glimmer-30B on 1× DGX Spark — BF16, SGLang, TP1 inference benchmark
Open this configuration in the LLM Inference Benchmark Explorer
| Model | Muse-Glimmer-30B |
|---|---|
| Parameters | 30B |
| Intelligence Index | 17.5 |
| Agentic Index | 8.5 |
| Device | 1× DGX Spark |
| Quantization | BF16 |
| Max C | 1 |
| Chat Capacity | 4 |
| Agentic Capacity | 1 |
| TP | — |
| DP | — |
| PP | — |
| Engine | SGLang |
| Speculative Decoding | — |
| C | TTFT (ms) | TPS (tok/s) | Status |
|---|---|---|---|
| 1 | 765 | 25.04 | PASS |
| 2 | 1002 | 22.75 | FAIL |
| 4 | 1106 | 20.50 | FAIL |
| 8 | 1190 | 17.42 | FAIL |
In OpenZeka's measurement, Muse-Glimmer-30B (30B parameters), served in BF16 format with SGLang on 1× DGX Spark, reached a generation speed of 25 tok/s per request and a time to first token (TTFT) of 765 ms with a single request.
Considering the speed targets and the available KV cache capacity, the estimated capacity is 4 users for chat use and 1 for agentic use. The realistic capacity will likely fall between these two values. In scenarios dominated by coding, tool use, long workflows and multi-agent use, capacity approaches the agentic estimate; where shorter interactions, standard conversations and lighter tasks dominate, it approaches the chat estimate.
Notes: max_model_len 131072
Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.
In OpenZeka's measurement, Muse-Glimmer-30B (30B parameters), served in BF16 format with SGLang on 1× DGX Spark, reached a generation speed of 25 tok/s per request and a time to first token (TTFT) of 765 ms with a single request.
Considering the speed targets and the available KV cache capacity, the estimated capacity is 4 users for chat use and 1 for agentic use. The realistic capacity will likely fall between these two values. In scenarios dominated by coding, tool use, long workflows and multi-agent use, capacity approaches the agentic estimate; where shorter interactions, standard conversations and lighter tasks dominate, it approaches the chat estimate.