Llama 4

Llama-4-Maverick-17B-128E-Instruct

Meta AI · open-restricted llama4

Parameters (B)401.584
Architecturemoe
Layers / KV heads / head dim48 / 8 / 128
Context window1048576
Modalitiesin: text, image; out: text
GGUFavailable
Commercial useyes

Minimum hardware (estimate)

At Q4_K_M and 8k context, total working set ≈ 246.0 GiB. On a machine with 64 GiB system RAM and no discrete GPU: Won't run. Limiting factor: No GPU and system RAM insufficient for weights + KV.

Open in fit advisor

Scores

BenchmarkValueUncertaintyRun bySource
GPQA Diamond67.0%unknownthird-partyepoch-ai
MATH Level 573.0%unknownthird-partyepoch-ai
OTIS Mock AIME 2024-202520.6%unknownthird-partyepoch-ai
FrontierMath0.7%unknownthird-partyepoch-ai
Aider polyglot15.6%unknownthird-partyepoch-ai

Provenance

HF: meta-llama/Llama-4-Maverick-17B-128E-Instruct · snapshot 2026-08-10