← Back to community benchmarks
Meta-Llama-3.1-8B-Instruct
Performance
4k
tokens
212.6
PP tok/s
20.0
TG tok/s
19270
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
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 223.0 | 22.4 | 4.9 GB | view |
| 4k | 212.6 | 20.0 | 5.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.4 | 1.00× |
| 2× | 43.6 | 1.95× |
| 4× | 52.9 | 2.36× |