← Back to community benchmarks
Llama-3.2-1B-Instruct
Performance
64k
tokens
193.9
PP tok/s
9.5
TG tok/s
338014
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,135 | 97.6 | 1.3 GB | view |
| 4k | 1,090 | 70.5 | 1.4 GB | view |
| 8k | 1,013 | 55.5 | 1.5 GB | view |
| 16k | 811.1 | 53.3 | 1.6 GB | view |
| 32k | 476.1 | 19.8 | 2.2 GB | view |
| 64k | 193.9 | 9.5 | 3.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 97.6 | 1.00× |
| 2× | 86.1 | 0.88× |
| 4× | 102.9 | 1.05× |
| 8× | 110.5 | 1.13× |