← Back to community benchmarks
Llama-3.2-1B-Instruct
Performance
4k
tokens
1,589
PP tok/s
119.8
TG tok/s
2578
TTFT (ms)
1.5
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 15.7.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,338 | 167.0 | 1.4 GB | view |
| 4k | 1,589 | 119.8 | 1.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 167.0 | 1.00× |
| 2× | 223.5 | 1.34× |
| 4× | 230.0 | 1.38× |
| 8× | 244.8 | 1.47× |