← Back to community benchmarks
Qwen3.5-9B
Performance
64k
tokens
265.8
PP tok/s
20.1
TG tok/s
246527
TTFT (ms)
10.8
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.6
macOS
macOS 26.4
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 310.8 | 56.5 | 6.7 GB | view |
| 4k | 316.9 | 53.6 | 7.0 GB | view |
| 8k | 313.6 | 51.0 | 7.1 GB | view |
| 32k | 280.6 | 34.5 | 8.7 GB | view |
| 64k | 265.8 | 20.1 | 10.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.5 | 1.00× |
| 2× | 66.8 | 1.18× |
| 4× | 73.1 | 1.29× |