Meta
Meta
/Llama 4 Scout

Quantizations

QuantQuantized bySizeDecodePrefillScoreActions
MLX Community
MLX Community
56.9 GB33.0 tok/s291.1 tok/sRuns poorly

Device Comparison

Results include trials with 4,096 input tokens and 1,024 output tokens only.

Decode / Prefill Speeds

1 device