Can 2x Tesla V100 32GB 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 13 tok/s generation with part of the model offloaded to system RAM (bnk v0.5.0, experts split VRAM/RAM (CPU offload), GSQ-RCO 2-bit; source).
Every measured result for DeepSeek V4.1 Flash on 2x Tesla V100 32GB
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| Dual Tesla V100 32 GB on EPYC 7402 (bnk engine) | GSQ-RCO 2-bit | bnk v0.5.0, experts split VRAM/RAM (CPU offload) | 13 CPU offload | source |
Memory: 2x Tesla V100 32GB has 64 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: RTX 5090
Other models measured on 2x Tesla V100 32GB: Qwen3.8 27B · 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.