← Back to community benchmarks
Qwen3.5-2B-OptiQ
Performance
1k
tokens
767.6
PP tok/s
49.5
TG tok/s
1334
TTFT (ms)
3.1
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 767.6 | 49.5 | 3.1 GB | current |
| 4k | 866.0 | 46.6 | 3.3 GB | view |
| 8k | 858.8 | 44.0 | 3.3 GB | view |
| 32k | 698.9 | 30.3 | 5.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.5 | 1.00× |
| 2× | 94.4 | 1.91× |
| 4× | 149.5 | 3.02× |