← Back to community benchmarks
Qwen3.5-4B-OptiQ
Performance
4k
tokens
702.8
PP tok/s
82.7
TG tok/s
5828
TTFT (ms)
4.1
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.7
macOS
macOS 15.3.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 614.4 | 86.1 | 4.0 GB | view |
| 4k | 702.8 | 82.7 | 4.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 86.1 | 1.00× |
| 2× | 132.9 | 1.54× |
| 4× | 160.9 | 1.87× |