← Back to community benchmarks
695690b33533b1f8b0395c1d6b4f00dc411353ef
Performance
1k
tokens
516.2
PP tok/s
41.5
TG tok/s
1984
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
36 GB
GPU Cores
18
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 516.2 | 41.5 | 14.3 GB | current |
| 4k | 562.8 | 40.3 | 14.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.5 | 1.00× |
| 2× | 63.7 | 1.53× |
| 4× | 78.4 | 1.89× |