← Back to community benchmarks
Qwen3.5-2B
Performance
1k
tokens
581.6
PP tok/s
4.6
TG tok/s
1761
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 581.6 | 4.6 | 6.8 GB | current |
| 4k | 702.8 | 4.6 | 6.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 4.6 | 1.00× |
| 2× | 9.5 | 2.07× |
| 4× | 18.9 | 4.11× |