Skip to content

Llama 4 Scout 17B 16E Instruct on DGX Station GB300: VRAM, speed and fit

Llama 4 Scout 17B 16E Instruct at 8-bit runs on the DGX Station GB300 with 672K of context at about 148 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on DGX Station GB300 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
234 GB
of 252 GB
Context
672K
auto
Speed
148 tok/s
29 when full
First reply
0.3 s
2K prompt

Where the memory goes

Model
108 GB
Context
126 GB
Overhead
1.0 GB
OS
0.0 GB
Free
17.5 GB
In RAM
0.0 GB
Memory
234 GB of 252 GB
Context
672K tokens · auto
Speed
148 tok/s · 29 when full
First reply
0.3 s for a 2K prompt
Running cost
$23/mo at home · $574/mo on a cloud 8× A40

Validation: Validated

What Llama 4 Scout 17B 16E Instruct on DGX Station GB300 was checked against
CheckTargetResultStatus
Fits in GPU memory252 GB usable234 GB neededPass
Headroom5% free17.5 GB free (7%)Pass
Context for chat16K or more672KPass
Writing speed15 tok/s or more148 tok/sPass
First replyunder 3 s, 2K prompt0.3 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
Llama 4 Scout 17B 16E Instruct
Parameters
109B, 18B active
Precision
8-bit (Q8_0)
Context
672K, 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
$574/mo
8× A40 at $4.72/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/Llama-4-Scout-17B-16E-Instruct-GGUF
vLLM
vllm serve meta-llama/Llama-4-Scout-17B-16E-Instruct

Llama 4 Scout 17B 16E Instruct on similar machines

All machines: Llama 4 Scout 17B 16E Instruct VRAM requirements. Everything that runs here: what can the DGX Station GB300 run?

Other models that run on DGX Station GB300

Questions

Can Llama 4 Scout 17B 16E Instruct run on DGX Station GB300?

Llama 4 Scout 17B 16E Instruct at 8-bit runs on the DGX Station GB300 with 672K of context at about 148 tokens a second.

Report VR-1OPK12H, calculated Nov 22, 2026 from published specs, not benchmarked.