← Back to community benchmarks
Qwen2.5-7B-Instruct
Performance
1k
tokens
112.9
PP tok/s
18.6
TG tok/s
9071
TTFT (ms)
4.7
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 112.9 | 18.6 | 4.7 GB | current |
| 4k | 105.1 | 15.0 | 5.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.6 | 1.00× |
| 2× | 27.0 | 1.45× |
| 4× | 18.1 | 0.97× |