← Back to community benchmarks
Qwen2.5-7B-Instruct
Performance
1k
tokens
256.9
PP tok/s
23.9
TG tok/s
3987
TTFT (ms)
4.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.4
macOS
macOS 15.7.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 256.9 | 23.9 | 4.5 GB | current |
| 4k | 255.1 | 21.9 | 4.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.9 | 1.00× |
| 2× | 45.7 | 1.91× |
| 4× | 60.7 | 2.54× |