Skip to content

DeepSeek V4 Flash on DGX Station GB300: VRAM, speed and fit

DeepSeek V4 Flash at FP4 + FP8 runs on the DGX Station GB300 with 1M of context at about 157 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Station GB300 · FP4 + FP8 · Ollama / LM Studio · Chat

GPU memory
162 GB
of 252 GB
Context
1M
auto
Speed
157 tok/s
130 when full
First reply
0.2 s
2K prompt

Where the memory goes

Model
155 GB
Context
6.1 GB
Overhead
841 MB
OS
0.0 GB
Free
89.7 GB
In RAM
0.0 GB
Memory
162 GB of 252 GB
Context
1M tokens · auto
Speed
157 tok/s · 130 when full
First reply
0.2 s for a 2K prompt
Running cost
$23/mo at home · $287/mo on a cloud 4× A40

Validation: Validated

What DeepSeek V4 Flash on DGX Station GB300 was checked against
CheckTargetResultStatus
Fits in GPU memory252 GB usable162 GB neededPass
Headroom5% free89.7 GB free (36%)Pass
Context for chat16K or more1MPass
Writing speed15 tok/s or more157 tok/sPass
First replyunder 3 s, 2K prompt0.2 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
DeepSeek V4 Flash
Parameters
284B, 13B active
Precision
FP4 + FP8
Context
1M, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
DGX Station GB300
GPU can use
252 GB of 252 GB
Spill space
480 GB LPDDR5X on the Grace CPU

Running cost

At home
$23/mo
1040 W at the wall
Renting instead
$287/mo
4× A40 at $2.36/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/DeepSeek-V4-Flash-0731-GGUF
vLLM
vllm serve deepseek-ai/DeepSeek-V4-Flash-0731
MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V4-Flash-0731-2.4bit-mixed

DeepSeek V4 Flash on similar machines

All machines: DeepSeek V4 Flash VRAM requirements. Everything that runs here: what can the DGX Station GB300 run?

Other models that run on DGX Station GB300

Questions

Can DeepSeek V4 Flash run on DGX Station GB300?

DeepSeek V4 Flash at FP4 + FP8 runs on the DGX Station GB300 with 1M of context at about 157 tokens a second.

Report VR-0L9RWDH, calculated Nov 22, 2026 from published specs, not benchmarked.