← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
484.5
PP tok/s
45.8
TG tok/s
2113
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M3 Pro (14c)
Memory
18 GB
GPU Cores
14
Software
oMLX
v0.2.6
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 484.5 | 45.8 | 4.0 GB | current |
| 4k | 486.0 | 43.0 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.8 | 1.00× |
| 2× | 87.0 | 1.90× |
| 4× | 108.4 | 2.37× |
| 8× | 113.4 | 2.48× |