Skip to content

Llama 4 Scout 17B 16E Instruct on 2× RTX 3090: VRAM, speed and fit

Llama 4 Scout 17B 16E Instruct at 2-bit runs on the 2× RTX 3090 with 28K of context at about 76 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 2× RTX 3090 · 2-bit (Q2_K) · Ollama / LM Studio · Chat

GPU memory
44.9 GB
of 48.0 GB
Context
28K
auto
Speed
76 tok/s
46 when full
First reply
1.9 s
2K prompt

Where the memory goes

Model
37.9 GB
Context
5.3 GB
Overhead
1.7 GB
OS
0.0 GB
Free
3.1 GB
Memory
44.9 GB of 48.0 GB
Context
28K tokens · auto
Speed
76 tok/s · 46 when full
First reply
1.9 s for a 2K prompt
Running cost
$11/mo at home · $66/mo on a cloud 2× RTX A5000

Validation: Validated

What Llama 4 Scout 17B 16E Instruct on 2× RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory48.0 GB usable44.9 GB neededPass
Headroom5% free3.1 GB free (6%)Pass
Context for chat16K or more28KPass
Writing speed15 tok/s or more76 tok/sPass
First replyunder 3 s, 2K prompt1.9 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
2-bit (Q2_K)
Context
28K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
2× RTX 3090
GPU can use
48.0 GB of 48.0 GB

Worth trying

  • 8-bit cache: Room for 56K context

Running cost

At home
$11/mo
500 W at the wall
Renting instead
$66/mo
2× RTX A5000 at $0.54/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

  • RTX 3090Too big
  • RTX 4090Too big
  • Radeon AI PRO R9700Too big
  • RTX 5090Too big
  • 2× RTX 4090Runs
  • RTX PRO 5000 Blackwell 48 GBRuns
  • RTX 6000 AdaRuns
  • L40SRuns

All machines: Llama 4 Scout 17B 16E Instruct VRAM requirements. Everything that runs here: what can the 2× RTX 3090 run?

Other models that run on 2× RTX 3090

Questions

Can Llama 4 Scout 17B 16E Instruct run on 2× RTX 3090?

Llama 4 Scout 17B 16E Instruct at 2-bit runs on the 2× RTX 3090 with 28K of context at about 76 tokens a second.

Report VR-1C67QPQ, calculated Nov 22, 2026 from published specs, not benchmarked.