← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
300.6
PP tok/s
61.0
TG tok/s
3407
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.3.5
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 300.6 | 61.0 | 3.4 GB | current |
| 4k | 317.6 | 56.1 | 4.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.0 | 1.00× |
| 2× | 70.3 | 1.15× |
| 4× | 72.4 | 1.19× |