Can 2x DGX Spark (GB10) run DeepSeek V4.1 Flash?
Probably only partly: the weights are larger than its memory, so part of the model likely ran from system RAM. Measured 74.9 tok/s generation with part of the model offloaded to system RAM (TensorFold Zig, 2 nodes, 1 stream, 1017 checkpoint, EXL3 2.9-bit + DSpark; source).
Every measured result for DeepSeek V4.1 Flash on 2x DGX Spark (GB10)
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| 2x DGX Spark: DeepSeek V4.1 Flash (1017) EXL3 2.9-bit on TensorFold Zig, 74.9 tok/s (Mia's AI Lab recipe) | 1017 checkpoint, EXL3 2.9-bit + DSpark | TensorFold Zig, 2 nodes, 1 stream | 74.9 CPU offload | source |
| 2x DGX Spark: DeepSeek V4.1 Flash EXL3 2.9-bit on vLLM, 31.6 tok/s (Mia's AI Lab recipe) | EXL3 2.9-bit | vLLM, 2 nodes, 1 stream | 31.6 CPU offload | source |
Memory: 2x DGX Spark (GB10) has 256 GB. DeepSeek V4.1 Flash weights are about 511 GB in its native format (vLLM recipe: 552B backbone + 196.6B Engram tables, 16B active per output token; official MXFP4/FP8 checkpoint ~511 GB). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.
Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.
All measured speeds for DeepSeek V4.1 Flash: best home rig for DeepSeek V4.1 Flash.
DeepSeek V4.1 Flash on other hardware: 2x Tesla V100 32GB · 4x DGX Spark (GB10) · Apple M3 Ultra · RTX 5090
Other models measured on 2x DGX Spark (GB10): GLM-5.3 Flash · MiMo V2.6 Flash · Qwen3.8 Flash-Next
Not enough VRAM? Rent before you buy. Run DeepSeek V4.1 Flash on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.