Skip to content

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

DeepSeek V4 Pro at 2-bit runs, spilling into system RAM, on the DGX Station GB300 with 1M of context at about 29 tokens a second.

Text generation · Chat · Ollama / LM Studio

Spills to RAM · on DGX Station GB300 · 2-bit (Q2_K) · Ollama / LM Studio · Chat

329 GB, slower

GPU memory
239 GB
of 252 GB
Context
1M
auto
Speed
29 tok/s
Fast
First reply
4.4 s
2K prompt

Where the memory goes

Model
559 GB
Context
8.7 GB
Overhead
937 MB
OS
0.0 GB
Free
0.0 GB
In RAM
329 GB
Memory
239 GB of 252 GB · 329 GB in system RAM
Context
1M tokens · auto
Speed
29 tok/s · fast
First reply
4.4 s for a 2K prompt
Running cost
$23/mo at home · $1,162/mo on a cloud 4× MI300X

Validation: Validated with conditions

What DeepSeek V4 Pro on DGX Station GB300 was checked against
CheckTargetResultStatus
Fits in GPU memory252 GB usable568 GB, 329 GB in RAMCheck
Headroom5% freeGPU full, rest in RAMCheck
Context for chat16K or more1MPass
Writing speed15 tok/s or more29 tok/sPass
First replyunder 3 s, 2K prompt4.4 sCheck

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 Pro
Parameters
1.6T, 49B active
Precision
2-bit (Q2_K)
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

Worth trying

  • 8× RTX PRO 6000 Blackwell: Runs it with 1M context
  • 8× H200 NVL: Runs it with 1M context

Running cost

At home
$23/mo
1040 W at the wall
Renting instead
$1,162/mo
4× MI300X at $9.56/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 21, 2026.

How to run it

llama.cpp
llama-server -hf unsloth/DeepSeek-V4-Pro-0813-GGUF
vLLM
vllm serve deepseek-ai/DeepSeek-V4-Pro
MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-V4-Pro-4bit

DeepSeek V4 Pro on similar machines

All machines: DeepSeek V4 Pro 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 Pro run on DGX Station GB300?

DeepSeek V4 Pro at 2-bit runs, spilling into system RAM, on the DGX Station GB300 with 1M of context at about 29 tokens a second.

Report VR-165YGOS, calculated Nov 22, 2026 from published specs, not benchmarked.