← Back to community benchmarks
Qwen3.5-4B-OptiQ
Performance
1k
tokens
630.6
PP tok/s
87.3
TG tok/s
1624
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.10
macOS
macOS 15.3.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 630.6 | 87.3 | 4.0 GB | current |
| 4k | 704.2 | 82.2 | 4.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 87.3 | 1.00× |
| 2× | 131.7 | 1.51× |
| 4× | 160.5 | 1.84× |