← Back to community benchmarks
Llama-3.2-3B-Instruct
Performance
1k
tokens
419.8
PP tok/s
47.9
TG tok/s
2442
TTFT (ms)
2.3
Peak mem (GB)
Hardware
Chip
M4 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.2.6
macOS
macOS 15.7.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 419.8 | 47.9 | 2.3 GB | current |
| 4k | 382.4 | 37.8 | 2.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.9 | 1.00× |
| 2× | 84.8 | 1.77× |
| 4× | 88.5 | 1.85× |