Llama 4 Scout 17B — VRAM, Speed & Local Setup

Name: LLM Configurator — GPU VRAM Checker
Author: LLM Configurator

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 5 kwietnia 2025

Model library → Llama 4 → Llama 4 Scout 17B

The most accessible Llama 4 model. 17B active parameters in a 109B MoE architecture with a massive 10M token context window. All 109B parameters must be resident in memory even though only 17B activate per token, so it needs roughly 67 GB at Q4_K_M — an 80 GB datacentre card, a 96 GB+ unified-memory machine, or multi-GPU. Meta states it fits a single H100 at int4.

Llama 4 Scout 17B needs about 67 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.

Specifications

Parameters	109 Billion (17B active)
Context window	10,000,000
Architecture	MoE (16 experts)
Provider	Meta
Licence	Llama 4 Community
Specified at	Q4_K_M
System RAM	16 GB
Record updated	2025-04-05

Licence

Llama Community — commercial use permitted. Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.

VRAM and Speed by Quantization

Modelled on a reference NVIDIA RTX 4090 (24 GB). Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.

Quant	Bits/weight	Weights	VRAM needed	Est. speed	Fit on 24 GB
Q2_K	2.63	35.8 GB	38.2 GB	~14 tok/s (est.)	Offloads to system RAM (slow)
Q3_K_M	3.41	46.5 GB	48.9 GB	~12 tok/s (est.)	Offloads to system RAM (slow)
Q4_K_M	4.83	65.8 GB	68.2 GB	—	Won't fit
Q5_K_M	5.67	77.3 GB	79.7 GB	—	Won't fit
Q6_K	6.56	89.4 GB	91.8 GB	—	Won't fit
Q8_0	8.50	115.8 GB	118.2 GB	—	Won't fit
F16	16.00	218 GB	220.4 GB	—	Won't fit

Want to set your own context length and KV-cache quantization? Use the interactive VRAM calculator.

Buy This HardwareRyzen AI Max+ 395 Laptop (Strix Halo, up to 128GB) — 96 GB VRAM · 120 W board power Deploy in the Cloud NowNVIDIA A100 80GB on RunPod — from $1.39/hr · rate checked 2026-07

or compare on Vast.ai from $0.77/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Recommended GPU

The cheapest catalogued GPU that runs Llama 4 Scout 17B is the AMD Ryzen AI Max+ 395 (96 GB).

Ujawnienie afiliacyjne: Niektóre odnośniki na tej stronie to linki afiliacyjne — jeśli dokonasz zakupu za ich pośrednictwem, LLM Configurator może otrzymać prowizję bez dodatkowych kosztów dla Ciebie. Jako uczestnik programu Amazon Associates, LLM Configurator zarabia na kwalifikujących się zakupach.

Ryzen AI Max+ 395 Laptop (Strix Halo, up to 128GB)

96 GB VRAM · 120 W board power

Ceny w 2026 są niestabilne — sprawdź aktualną ofertę.

Sprawdź cenę na Amazon

How to Run Llama 4 Scout 17B

Install Ollama, then run:

ollama run llama4:scout

Weights on Hugging Face: meta-llama/Llama-4-Scout-17B-16E-Instruct.

Best for: chat, rag, long context, reasoning.

Can I Run Llama 4 Scout 17B on My GPU?

Other Llama 4 Sizes

Llama 4 Maverick 17B — about 242 GB VRAM at Q4_K_M

Llama 4 Scout 17B — Frequently Asked Questions

How much VRAM does Llama 4 Scout 17B need?

About 67 GB at Q4_K_M — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Llama 4 Scout 17B run on an RTX 4090 (24 GB)?

No. Llama 4 Scout 17B needs about 67 GB at Q4_K_M, more than a single RTX 4090's 24 GB. It needs a larger card, several GPUs, or Apple Silicon with enough unified memory — or it runs with part of the weights offloaded to system RAM, which is much slower.

How do I run Llama 4 Scout 17B locally?

Install Ollama and run `ollama run llama4:scout`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does Llama 4 come in?

Llama 4 Scout 17B (67 GB), Llama 4 Maverick 17B (242 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.

← All Llama 4 models | VRAM calculator | Check your own hardware