← Back to community benchmarks
Qwen2-VL-2B-Instruct
Performance
16k
tokens
1,587
PP tok/s
83.7
TG tok/s
10327
TTFT (ms)
2.5
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
24 GB
GPU Cores
20
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,842 | 119.0 | 2.2 GB | view |
| 4k | 2,002 | 108.7 | 2.3 GB | view |
| 8k | 1,884 | 97.6 | 2.5 GB | view |
| 16k | 1,587 | 83.7 | 2.5 GB | current |
| 32k | 1,185 | 67.7 | 3.0 GB | view |
| 64k | 740.0 | 48.2 | 3.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 119.0 | 1.00× |
| 2× | 158.7 | 1.33× |
| 4× | 203.6 | 1.71× |
| 8× | 242.1 | 2.03× |