← Back to community benchmarks
Qwen3-VL-4B-Instruct
Performance
4k
tokens
376.9
PP tok/s
29.7
TG tok/s
10867
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 411.2 | 37.1 | 3.6 GB | view |
| 4k | 376.9 | 29.7 | 4.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.1 | 1.00× |
| 2× | 68.9 | 1.86× |
| 4× | 87.9 | 2.37× |