← Back to community benchmarks
Qwen2.5-7B-Instruct
Performance
4k
tokens
851.2
PP tok/s
26.5
TG tok/s
4812
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 837.3 | 28.9 | 4.5 GB | view |
| 4k | 851.2 | 26.5 | 4.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.9 | 1.00× |
| 2× | 57.7 | 2.00× |
| 4× | 82.5 | 2.85× |