← Back to community benchmarks
Qwen3-VL-4B-Instruct
Performance
1k
tokens
411.2
PP tok/s
37.1
TG tok/s
2491
TTFT (ms)
3.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 411.2 | 37.1 | 3.6 GB | current |
| 4k | 376.9 | 29.7 | 4.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.1 | 1.00× |
| 2× | 68.9 | 1.86× |
| 4× | 87.9 | 2.37× |