← Back to community benchmarks
Qwen2.5-14B-Instruct
Performance
1k
tokens
183.4
PP tok/s
14.8
TG tok/s
5583
TTFT (ms)
8.5
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
18 GB
GPU Cores
18
Software
oMLX
v0.2.8
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 183.4 | 14.8 | 8.5 GB | current |
| 4k | 175.8 | 13.4 | 9.2 GB | view |
| 8k | 157.7 | 11.8 | 10.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.8 | 1.00× |
| 2× | 28.4 | 1.92× |
| 4× | 42.0 | 2.84× |
| 8× | 41.4 | 2.80× |