← Back to community benchmarks
Qwen3.5 2b
Performance
1k
tokens
609.9
PP tok/s
5.3
TG tok/s
1679
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 | 609.9 | 5.3 | 6.8 GB | current |
| 4k | 723.7 | 5.2 | 6.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 5.3 | 1.00× |
| 2× | 10.2 | 1.92× |
| 4× | 20.2 | 3.81× |