← Back to community benchmarks
Llama-3.2-3B-Instruct
Performance
64k
tokens
181.5
PP tok/s
8.7
TG tok/s
361167
TTFT (ms)
11.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 548.9 | 28.5 | 3.7 GB | view |
| 4k | 513.6 | 25.4 | 4.1 GB | view |
| 8k | 468.5 | 22.6 | 4.5 GB | view |
| 16k | 388.6 | 18.3 | 5.4 GB | view |
| 32k | 282.2 | 13.5 | 7.3 GB | view |
| 64k | 181.5 | 8.7 | 11.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.5 | 1.00× |
| 2× | 54.8 | 1.92× |
| 4× | 85.2 | 2.99× |