Can the DGX Spark (GB10) run Muse Glimmer?
Yes. Muse Glimmer fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 11.8 GB needed), running at an estimated 16 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
Muse Glimmer (18.1B) on 128 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 10 GB | 11.8 GB | Fits easily | ~16 tok/s |
| Q5_K_M | 13 GB | 14.8 GB | Fits easily | ~12 tok/s |
| Q8_0 | 19 GB | 20.8 GB | Fits easily | ~8.3 tok/s |
| FP16 | 36 GB | 37.8 GB | Fits easily | ~4.4 tok/s |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the DGX Spark (GB10)'s 273.2 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
Compare
Same model, other hardware - and other models on this card
Muse Glimmer on other hardware
- RTX 5090~103 tok/s
- RTX 5090 D~103 tok/s
- RTX 6000D~90 tok/s
- RTX 4090~63 tok/s
- RTX 3090~55 tok/s
- Radeon RX 7900 XTX~55 tok/s
- RTX 5080~55 tok/s
- RTX 3080 Ti~52 tok/s
Also runs on the DGX Spark (GB10)
- gpt-oss-120b~35 tok/s
- Llama 3.3 70B~3.9 tok/s
- deepseek-v4-flash-0731-spark~4.5 tok/s
- Qwen3.6 35B A3B~60 tok/s
- dolphin-2.9.1-yi-1.5-34b~7.8 tok/s
- Laguna-XS-2.1~8.3 tok/s
- Gemma 4 31B~8.3 tok/s
- OTel-2.0-LLM-31B-IT~8.3 tok/s
Frequently asked
Quick answers
Can the NVIDIA DGX Spark (GB10) run Muse Glimmer?
Yes. Muse Glimmer fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 11.8 GB needed), running at an estimated 16 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does Muse Glimmer need?
About 10 GB of weights at Q4_K_M, 19 GB at Q8_0 and 36 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Muse Glimmer on the DGX Spark (GB10)?
Roughly 16 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the DGX Spark (GB10)'s 273.2 GB/s memory bandwidth.