Can RTX 5090 run DeepSeek V4.1 Flash?

Partly: part of the model runs from system RAM (CPU offload, per the source). Measured 24.9 tok/s generation with part of the model offloaded to system RAM (Project Maya 1.1.21 (maya-ds4), Maya-S (experts 2-3 bit), partly streamed from SSD; source).

Every measured result for DeepSeek V4.1 Flash on RTX 5090

Build	Quant / setup	Engine	tok/s
Ryzen 9 9950X3D + RTX 5090 + 128 GB DDR5: four big MoEs with experts offloaded to RAM (Qwen3.8 Flash-Next 78.8 tok/s)	Maya-S (experts 2-3 bit), partly streamed from SSD	Project Maya 1.1.21 (maya-ds4)	24.9 CPU offload	source

Memory: RTX 5090 has 32 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 · Apple M3 Ultra

Other models measured on RTX 5090: GLM-5.3 Flash · Gemma 4 12B · Gemma 4 26B-A4B · Gemma 4 31B · Nemotron 3.5 Bolt 74B-A9B · Ornith 1.5 122B · Qwen3.5 9B · Qwen3.6 27B · Qwen3.6 35B-A3B · Qwen3.8 27B · Qwen3.8 Flash-Next · gpt-oss 20B

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.