← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
573.6
PP tok/s
47.3
TG tok/s
1785
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
18 GB
GPU Cores
18
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 573.6 | 47.3 | 4.0 GB | current |
| 4k | 615.3 | 45.9 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.3 | 1.00× |
| 2× | 89.8 | 1.90× |
| 4× | 138.0 | 2.92× |