← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
322.8
PP tok/s
60.1
TG tok/s
3172
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 322.8 | 60.1 | 4.0 GB | current |
| 4k | 323.6 | 55.8 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 60.1 | 1.00× |
| 2× | 69.1 | 1.15× |
| 4× | 73.2 | 1.22× |