← Back to community benchmarks
Qwen3-VL-4B-Instruct
Performance
1k
tokens
310.8
PP tok/s
36.8
TG tok/s
3294
TTFT (ms)
3.6
Peak mem (GB)
Hardware
Chip
M4 (8c)
Memory
16 GB
GPU Cores
8
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 | 310.8 | 36.8 | 3.6 GB | current |
| 4k | 284.0 | 30.0 | 4.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.8 | 1.00× |
| 2× | 64.9 | 1.76× |
| 4× | 69.5 | 1.89× |