← Back to community benchmarks
Meta-Llama-3.1-8B-Instruct
Performance
4k
tokens
213.9
PP tok/s
20.2
TG tok/s
19150
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
4,096