Skip to content

Llama 4 Scout 17B 16E Instruct on H100 SXM: VRAM, speed and fit

Llama 4 Scout 17B 16E Instruct at 5-bit runs on the H100 SXM with 16K of context at about 120 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on H100 SXM · 5-bit (Q5_K_M) · Ollama / LM Studio · Chat

GPU memory
76.0 GB
of 80.0 GB
Context
16K
auto
Speed
120 tok/s
Very fast
First reply
0.8 s
2K prompt

Where the memory goes

Model
72.0 GB
Context
3.0 GB
Overhead
1.0 GB
OS
0.0 GB
Free
4.0 GB
Memory
76.0 GB of 80.0 GB
Context
16K tokens · auto
Speed
120 tok/s · very fast
First reply
0.8 s for a 2K prompt
Running cost
$11/mo at home · $122/mo on a cloud 4× RTX A4500

Validation: Validated

What Llama 4 Scout 17B 16E Instruct on H100 SXM was checked against
CheckTargetResultStatus
Fits in GPU memory80.0 GB usable76.0 GB neededPass
Headroom5% free4.0 GB free (5%)Pass
Context for chat16K or more16KPass
Writing speed15 tok/s or more120 tok/sPass
First replyunder 3 s, 2K prompt0.8 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
5-bit (Q5_K_M)
Context
16K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
H100 SXM
GPU can use
80.0 GB of 80.0 GB

Worth trying

  • 8-bit cache: Room for 28K context

Running cost

At home
$11/mo
500 W at the wall
Renting instead
$122/mo
4× RTX A4500 at $1.00/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 H100 SXM run?

Other models that run on H100 SXM

Questions

Can Llama 4 Scout 17B 16E Instruct run on H100 SXM?

Llama 4 Scout 17B 16E Instruct at 5-bit runs on the H100 SXM with 16K of context at about 120 tokens a second.

Report VR-1G7I03W, calculated Nov 22, 2026 from published specs, not benchmarked.