Skip to content

Llama 4 Scout 17B 16E Instruct on M3 Ultra 256 GB: VRAM, speed and fit

Llama 4 Scout 17B 16E Instruct at 8-bit runs on the M3 Ultra 256 GB with 384K of context at about 23 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M3 Ultra 256 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
244 GB
of 256 GB
Context
384K
auto
Speed
23 tok/s
5.3 when full
First reply
11 s
2K prompt

Where the memory goes

Model
108 GB
Context
72.0 GB
Overhead
811 MB
OS
64.0 GB
Free
11.7 GB
Memory
244 GB of 256 GB
Context
384K tokens · auto
Speed
23 tok/s · 5.3 when full
First reply
11 s for a 2K prompt
Running cost
$3.55/mo at home · $287/mo on a cloud 4× A40

Validation: Not validated

What Llama 4 Scout 17B 16E Instruct on M3 Ultra 256 GB was checked against
CheckTargetResultStatus
Fits in GPU memory192 GB usable180 GB neededPass
Headroom5% free11.7 GB free (6%)Pass
Context for chat16K or more384KPass
Writing speed15 tok/s or more23 tok/sPass
First replyunder 3 s, 2K prompt11 sFails

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
384K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M3 Ultra 256 GB
GPU can use
192 GB of 256 GB

Running cost

At home
$3.55/mo
162 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 21, 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 M3 Ultra 256 GB run?

Other models that run on M3 Ultra 256 GB

Questions

Can Llama 4 Scout 17B 16E Instruct run on M3 Ultra 256 GB?

Llama 4 Scout 17B 16E Instruct at 8-bit runs on the M3 Ultra 256 GB with 384K of context at about 23 tokens a second.

Report VR-0DRRZZ7, calculated Nov 22, 2026 from published specs, not benchmarked.