← Back to community benchmarks
Qwen3.5-2B-OptiQ
Performance
4k
tokens
865.8
PP tok/s
46.6
TG tok/s
4731
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 765.3 | 49.4 | 3.1 GB | view |
| 4k | 865.8 | 46.6 | 3.3 GB | current |
| 8k | 857.7 | 43.9 | 3.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.4 | 1.00× |
| 2× | 93.3 | 1.89× |
| 4× | 150.8 | 3.05× |