what/llm/can/i/run

models/meta-llama-llama-4-scout-17b-16e-instruct

Llama 4 Scout 17B 16E

Sources arena · Confidence C

params

109B

MoE total

bench sources

1

single

context

—

max tokens

license

Llama

community

▸Model meta

canonical: meta-llama/Llama-4-Scout-17B-16E-Instruct
parameters: 109B
organization: Meta
license: Llama
context: —
downloads: —

▸Benchmark breakdown

▸Hardware fit matrix

by gpu tier	Q2_K 40.9 GB	Q4_K_M 54.5 GB	Q5_K_M 68.1 GB	Q6_K 81.8 GB	Q8_0 109.0 GB	FP16 218.0 GB
8 GB tier rtx 3050 · 4060
12 GB tier rtx 3060 · 4070
16 GB tier rtx 4080 · 4060 ti 16g
24 GB tier rtx 3090 · 4090
32 GB tier rtx 5090 · m3 max
48 GB tier a6000 · m3 max 64	OK 13 t/s
80 GB tier h100 · m3 ultra 128	GREAT 45 t/s	GREAT 34 t/s	OK 27 t/s

full fit · production speed tight fit · usabledoesn't fit

Get personalized ranking

Tell us your machine — we'll tell you if this is actually your best pick, or what's better.

Rank for my hardware