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

ModelMuse-Glimmer-30B
Parameters30B
Intelligence Index17.5
Agentic Index8.5
Device1× DGX Spark
QuantizationBF16
Max C1
Chat Capacity4
Agentic Capacity1
TP—
DP—
PP—
EngineSGLang
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
176525.04PASS
2100222.75FAIL
4110620.50FAIL
8119017.42FAIL

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.