← Back to community benchmarks
Qwen2-VL-7B-Instruct
Performance
1k
tokens
313.8
PP tok/s
40.4
TG tok/s
3263
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 313.8 | 40.4 | 4.8 GB | current |
| 4k | 314.0 | 36.9 | 4.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.4 | 1.00× |
| 2× | 59.6 | 1.48× |
| 4× | 62.1 | 1.54× |