← Back to community benchmarks
Qwen3-VL-32B-Instruct
Performance
1k
tokens
191.4
PP tok/s
22.7
TG tok/s
5351
TTFT (ms)
18.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 191.4 | 22.7 | 18.0 GB | current |
| 4k | 189.6 | 20.7 | 18.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.7 | 1.00× |
| 2× | 42.0 | 1.85× |
| 4× | 48.7 | 2.15× |