← Back to community benchmarks
Llama-3.2-3B-Instruct
Performance
1k
tokens
1,126
PP tok/s
125.7
TG tok/s
910
TTFT (ms)
2.5
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.2.7
macOS
macOS 26.0.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,126 | 125.7 | 2.5 GB | current |
| 4k | 1,145 | 101.6 | 2.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 125.7 | 1.00× |
| 2× | 176.9 | 1.41× |
| 4× | 192.1 | 1.53× |