Llama 4 Scout 17B 16E

Frontier

729.0KDownloads1.3KLikesApr 2025Released10.5M tokensContextLlama 4 CommunityLicense66 GoodQuality

Llama 4 Scout 17B 16E (109B parameters) requires approximately 71.2 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 17B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 82 GB of VRAM.

Get started

— copy & paste to run locally

Copy-paste commands to run Llama 4 Scout 17B 16E on your machine.

Run

lms load Llama-4-Scout-17B-16E-Instruct && lms server start

Quick specs

Parameters109B (17B active)

Architecturemoe (MoE)

Context10.5M tokens

Modalitytext+vision

Min RAM42.5 GB

Rec. RAM66.5 GB (Q4_K_M)

LicenseLlama 4 Community

FamilyLlama

✓ Vision✓ Chat✓ Reasoning

About this model

Llama 4 Scout is Meta's efficient Mixture-of-Experts model with 17B active parameters across 16 experts. Supports a 10M token context window and natively handles text, images, and video inputs.

Related models

Your hardware

Detecting...

Quick picks

Best budgetA

MacBook Pro M3 Max 128GB~$2,499 — 9 tok/s

Best overallA

AMD Instinct MI250X 128GB~$15,000 — 95 tok/s

Best hardware

Top picks for Llama 4 Scout 17B 16E

AMD Instinct MI250X 128GBA

128 GB

AMD Instinct MI300A 128GBA

128 GB

👁 Intel

Gaudi 3 128GBA

128 GB

AMD Instinct MI250 128GBA

128 GB

👁 Intel

Intel Data Center GPU Max 1550 128GBA

128 GB

Run this model

Llama 4 Scout 17B 16E on AMD Instinct MI250X 128GB Llama 4 Scout 17B 16E on AMD Instinct MI300A 128GB Llama 4 Scout 17B 16E on Gaudi 3 128GB

Quantization options

VRAM estimates by quant level

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	42.5 GB	Low	—
Q3_K_S	3	53.4 GB	Low	—
NVFP4	4	61.0 GB	Medium	—
Q4_K_M	4	66.5 GB	Medium	—
Q5_K_M	5	78.5 GB	High	—
Q6_K	6	89.4 GB	High	—
Q8_0	8	116.6 GB	Very High	—
F16	16	223.5 GB	Maximum	—

Quality benchmarks