← Back to community benchmarks
Llama-3.2-3B-Instruct
Performance
64k
tokens
275.5
PP tok/s
13.4
TG tok/s
237884
TTFT (ms)
11.2
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,134 | 76.7 | 3.9 GB | view |
| 4k | 746.4 | 65.7 | 4.3 GB | view |
| 64k | 275.5 | 13.4 | 11.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 76.7 | 1.00× |
| 2× | 82.9 | 1.08× |
| 4× | 85.9 | 1.12× |
| 8× | 115.2 | 1.50× |