← Back to community benchmarks
Qwen3-VL-4B-Instruct
Performance
1k
tokens
405.7
PP tok/s
21.8
TG tok/s
2524
TTFT (ms)
5.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 405.7 | 21.8 | 5.5 GB | current |
| 4k | 370.9 | 19.3 | 5.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.8 | 1.00× |
| 2× | 41.8 | 1.92× |
| 4× | 67.2 | 3.08× |