← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
319.2
PP tok/s
54.0
TG tok/s
12832
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.2.10
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 317.0 | 56.5 | 6.7 GB | view |
| 4k | 319.2 | 54.0 | 7.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.5 | 1.00× |
| 2× | 67.6 | 1.20× |
| 4× | 73.5 | 1.30× |
| 8× | 60.2 | 1.07× |