← Back to community benchmarks
Qwen3.5-4B
Performance
64k
tokens
427.4
PP tok/s
26.8
TG tok/s
153352
TTFT (ms)
9.9
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
64 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 646.9 | 48.4 | 5.9 GB | view |
| 4k | 648.6 | 45.9 | 6.1 GB | view |
| 64k | 427.4 | 26.8 | 9.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.4 | 1.00× |
| 2× | 89.4 | 1.85× |
| 4× | 105.0 | 2.17× |
| 8× | 112.5 | 2.32× |