Skip to content

Llama 4 Scout 17B 16E Instruct on 4× RTX 3090: VRAM, speed and fit

Llama 4 Scout 17B 16E Instruct at 6-bit runs on the 4× RTX 3090 with 24K of context at about 39 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 4× RTX 3090 · 6-bit (Q6_K) · Ollama / LM Studio · Chat

GPU memory
90.6 GB
of 96.0 GB
Context
24K
auto
Speed
39 tok/s
30 when full
First reply
1.0 s
2K prompt

Where the memory goes

Model
83.0 GB
Context
4.5 GB
Overhead
3.2 GB
OS
0.0 GB
Free
5.4 GB
Memory
90.6 GB of 96.0 GB
Context
24K tokens · auto
Speed
39 tok/s · 30 when full
First reply
1.0 s for a 2K prompt
Running cost
$20/mo at home · $131/mo on a cloud 4× RTX A5000

Validation: Validated

What Llama 4 Scout 17B 16E Instruct on 4× RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable90.6 GB neededPass
Headroom5% free5.4 GB free (6%)Pass
Context for chat16K or more24KPass
Writing speed15 tok/s or more39 tok/sPass
First replyunder 3 s, 2K prompt1.0 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
6-bit (Q6_K)
Context
24K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
4× RTX 3090
GPU can use
96.0 GB of 96.0 GB

Worth trying

  • 8-bit cache: Room for 48K context

Running cost

At home
$20/mo
920 W at the wall
Renting instead
$131/mo
4× RTX A5000 at $1.08/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 4× RTX 3090 run?

Other models that run on 4× RTX 3090

Questions

Can Llama 4 Scout 17B 16E Instruct run on 4× RTX 3090?

Llama 4 Scout 17B 16E Instruct at 6-bit runs on the 4× RTX 3090 with 24K of context at about 39 tokens a second.

Report VR-03JM7F0, calculated Nov 22, 2026 from published specs, not benchmarked.