← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
443.0
PP tok/s
18.1
TG tok/s
2312
TTFT (ms)
9.4
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 15.7.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 443.0 | 18.1 | 9.4 GB | current |
| 4k | 460.7 | 16.3 | 9.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.1 | 1.00× |
| 2× | 13.3 | 0.73× |
| 4× | 27.1 | 1.50× |