Llama 4 Scout

Llama 4 Scout loads in 67 GB at Q4_K_M and is comfortable from 96 GB of memory, Macs included from the MacBook Pro M5 Max 128GB. Below: the full memory math, the cheapest card that runs it well, and the fastest machine we track.

PARAMETERS

109B (17B active)

FORMAT

Q4_K_M

MIN MEMORY

96 GB

BEST FOR

Long context, Quality, Multimodal

Memory math

Weights (Q4_K_M)

67 GB

+ KV cache (16k)

~6.0 GB

Total at 16k

~73.0 GB

Comfortable from

96 GB

KV = fp16 estimate (q8_0 cache roughly halves it). "Comfortable" = weights + KV within the engine's tiered budget (~70-85% of memory).

Hardware snapshot

Cheapest GPU

AMD Ryzen AI Max+ 395 (Strix Halo)

~7 tok/s est. — ~$3,847 used (as of 2026-07-31)

Fastest

NVIDIA RTX PRO 6000 Blackwell

~35 tok/s est.

Runs on a Mac?

MacBook Pro M5 Max 128GB

~16 tok/s est.

Go deeper

Every Llama 4 Scout quant by real GGUF file size Best hardware for Llama 4 Scout: cheapest, best value, fastest

More Llama models

Llama 3.2 1B Instruct Llama 3.2 3B Instruct Llama 3.1 8B Instruct Llama 3.1 70B Instruct Llama 3.3 70B Instruct Llama 4 Maverick Llama 3.1 405B Instruct

Frequently asked questions

How much memory does Llama 4 Scout need?

67 GB for the Q4_K_M weights, plus ~6.0 GB of KV-cache at 16k context — about 73.0 GB total. Comfortable from 96 GB of VRAM or unified memory.

Does Llama 4 Scout run on a Mac?

Yes — from the MacBook Pro M5 Max 128GB (~16 tok/s est.). Unified memory means the RAM budget is the only limit.

What is the cheapest GPU for Llama 4 Scout?

The AMD Ryzen AI Max+ 395 (Strix Halo) is the cheapest tracked card that runs Llama 4 Scout comfortably — ~7 tok/s est. at ~$3,847 used (as of 2026-07-31).

Cite this page

ModelFit: Llama 4 Scout — specs, memory math and hardware verdicts.
https://modelfit.io/models/llama4-scout/ (dataset updated 2026-09-03, CC BY 4.0).