← Back to community benchmarks
Qwen2.5-VL-7B-Instruct
Performance
1k
tokens
731.7
PP tok/s
70.6
TG tok/s
1400
TTFT (ms)
6.1
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 731.7 | 70.6 | 6.1 GB | current |
| 4k | 597.3 | 48.8 | 6.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.6 | 1.00× |
| 2× | 74.4 | 1.05× |
| 4× | 88.0 | 1.25× |