← Back to community benchmarks
Qwen3.5-2B
Performance
1k
tokens
999.6
PP tok/s
46.9
TG tok/s
1024
TTFT (ms)
3.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 999.6 | 46.9 | 3.2 GB | current |
| 4k | 1,046 | 46.8 | 3.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.9 | 1.00× |
| 2× | 95.1 | 2.03× |
| 4× | 149.3 | 3.18× |