Can the DGX Spark (GB10) run deepseek-v4-flash-0731-spark?
Yes. deepseek-v4-flash-0731-spark fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 36.8 GB needed), running at an estimated 4.5 tok/s. There's room for up to FP16 if you want higher quality.
Every quantization
deepseek-v4-flash-0731-spark (60.3B) on 128 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 35 GB | 36.8 GB | Fits easily | ~4.5 tok/s |
| Q5_K_M | 43 GB | 44.8 GB | Fits easily | ~3.6 tok/s |
| Q8_0 | 65 GB | 66.8 GB | Fits easily | ~2.4 tok/s |
| FP16 | 121 GB | 122.8 GB | Tight | ~1.3 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
deepseek-v4-flash-0731-spark on other hardware
- RTX 6000D~26 tok/s
- MacBook Pro 16" M4 Max~8.9 tok/s
- RTX Spark N1X (128 GB)~4.5 tok/s
Also runs on the DGX Spark (GB10)
- gpt-oss-120b~35 tok/s
- Llama 3.3 70B~3.9 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
- Qwen3 32B~8.3 tok/s
Frequently asked
Quick answers
Can the NVIDIA DGX Spark (GB10) run deepseek-v4-flash-0731-spark?
Yes. deepseek-v4-flash-0731-spark fits the DGX Spark (GB10)'s 128 GB at Q4_K_M (about 36.8 GB needed), running at an estimated 4.5 tok/s. There's room for up to FP16 if you want higher quality.
How much VRAM does deepseek-v4-flash-0731-spark need?
About 35 GB of weights at Q4_K_M, 65 GB at Q8_0 and 121 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is deepseek-v4-flash-0731-spark on the DGX Spark (GB10)?
Roughly 4.5 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.