← Back to community benchmarks
Qwen2.5-7B-Instruct
Performance
1k
tokens
400.4
PP tok/s
54.2
TG tok/s
2557
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 400.4 | 54.2 | 4.8 GB | current |
| 4k | 397.1 | 49.6 | 4.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.2 | 1.00× |
| 2× | 83.5 | 1.54× |
| 4× | 92.7 | 1.71× |