← Back to community benchmarks
Llama-3.2-1B-Instruct
Performance
1k
tokens
891.5
PP tok/s
104.1
TG tok/s
1150
TTFT (ms)
1.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 891.5 | 104.1 | 1.3 GB | current |
| 4k | 952.3 | 75.7 | 1.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 104.1 | 1.00× |
| 2× | 151.9 | 1.46× |
| 4× | 161.0 | 1.55× |