← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
487.6
PP tok/s
4.4
TG tok/s
2100
TTFT (ms)
22.8
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.2.7
macOS
macOS 15.7
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 487.6 | 4.4 | 22.8 GB | current |
| 4k | 591.0 | 4.3 | 23.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 4.4 | 1.00× |
| 2× | 8.0 | 1.82× |
| 4× | 15.7 | 3.57× |