← Back to community benchmarks
Llama-3.2-3B-Instruct
Performance
1k
tokens
547.3
PP tok/s
46.3
TG tok/s
1873
TTFT (ms)
2.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 547.3 | 46.3 | 2.3 GB | current |
| 4k | 507.6 | 38.2 | 2.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.3 | 1.00× |
| 2× | 83.6 | 1.81× |
| 4× | 113.3 | 2.45× |