← Back to community benchmarks
Llama-3.2-1B-Instruct
Performance
16k
tokens
898.6
PP tok/s
57.1
TG tok/s
18234
TTFT (ms)
1.6
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,249 | 102.4 | 1.3 GB | view |
| 4k | 1,216 | 76.7 | 1.4 GB | view |
| 8k | 1,130 | 59.3 | 1.5 GB | view |
| 16k | 898.6 | 57.1 | 1.6 GB | current |
| 32k | 596.2 | 32.2 | 2.2 GB | view |
| 64k | 278.2 | 8.1 | 3.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 102.4 | 1.00× |
| 2× | 67.9 | 0.66× |
| 4× | 95.4 | 0.93× |
| 8× | 140.2 | 1.37× |