← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
313.4
PP tok/s
55.8
TG tok/s
3267
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 313.4 | 55.8 | 6.7 GB | current |
| 4k | 317.3 | 53.9 | 7.0 GB | view |
| 8k | 315.0 | 50.6 | 7.1 GB | view |
| 16k | 307.2 | 43.8 | 7.6 GB | view |
| 32k | 294.2 | 34.3 | 8.7 GB | view |
| 64k | 262.2 | 13.9 | 11.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 55.8 | 1.00× |
| 2× | 44.0 | 0.79× |
| 4× | 71.2 | 1.28× |
| 8× | 59.0 | 1.06× |