← Back to community benchmarks
Qwen3-VL-4B-Instruct
Performance
4k
tokens
320.4
PP tok/s
30.3
TG tok/s
12785
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 353.2 | 36.9 | 3.6 GB | view |
| 4k | 320.4 | 30.3 | 4.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.9 | 1.00× |
| 2× | 64.0 | 1.73× |
| 4× | 70.5 | 1.91× |