← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
754.2
PP tok/s
70.0
TG tok/s
1358
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 754.2 | 70.0 | 6.7 GB | current |
| 4k | 772.1 | 67.4 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.0 | 1.00× |
| 2× | 102.8 | 1.47× |
| 4× | 121.1 | 1.73× |