← Back to community benchmarks

Llama-3.2-1B-Instruct

M1 Max (32c) · 64 GB · 4bit · 2026-03-17
Performance
4k
tokens
2,914
PP tok/s
193.0
TG tok/s
1406
TTFT (ms)
1.5
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.2.13
macOS macOS 15.7.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,282 250.0 1.4 GB view
4k 2,914 193.0 1.5 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 250.0 1.00×
2× 360.2 1.44×
4× 409.9 1.64×