Skip to content

Llama 4 Scout 17B 16E Instruct on M3 Ultra 96 GB: VRAM, speed and fit

Llama 4 Scout 17B 16E Instruct at 4-bit runs on the M3 Ultra 96 GB with 32K of context at about 37 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M3 Ultra 96 GB · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat

GPU memory
92.1 GB
of 96.0 GB
Context
32K
auto
Speed
37 tok/s
25 when full
First reply
11 s
2K prompt

Where the memory goes

Model
61.3 GB
Context
6.0 GB
Overhead
811 MB
OS
24.0 GB
Free
3.9 GB
Memory
92.1 GB of 96.0 GB
Context
32K tokens · auto
Speed
37 tok/s · 25 when full
First reply
11 s for a 2K prompt
Running cost
$3.55/mo at home · $122/mo on a cloud 4× RTX A4500

Validation: Not validated

What Llama 4 Scout 17B 16E Instruct on M3 Ultra 96 GB was checked against
CheckTargetResultStatus
Fits in GPU memory72.0 GB usable68.1 GB neededPass
Headroom5% free3.9 GB free (5%)Pass
Context for chat16K or more32KPass
Writing speed15 tok/s or more37 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
4-bit (Q4_K_M)
Context
32K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M3 Ultra 96 GB
GPU can use
72.0 GB of 96.0 GB

Worth trying

  • 8-bit cache: Room for 60K context

Running cost

At home
$3.55/mo
162 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 M3 Ultra 96 GB run?

Other models that run on M3 Ultra 96 GB

Questions

Can Llama 4 Scout 17B 16E Instruct run on M3 Ultra 96 GB?

Llama 4 Scout 17B 16E Instruct at 4-bit runs on the M3 Ultra 96 GB with 32K of context at about 37 tokens a second.

Report VR-0A2VJAX, calculated Nov 22, 2026 from published specs, not benchmarked.