← Back to community benchmarks
Qwen3-VL-4B-Instruct
Performance
1k
tokens
144.5
PP tok/s
20.7
TG tok/s
7087
TTFT (ms)
3.6
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 144.5 | 20.7 | 3.6 GB | current |
| 4k | 133.4 | 18.1 | 4.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.7 | 1.00× |
| 2× | 31.3 | 1.51× |
| 4× | 29.9 | 1.44× |