← Back to community benchmarks
Qwen3.5-9B
Performance
64k
tokens
310.3
PP tok/s
14.6
TG tok/s
211216
TTFT (ms)
12.2
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.3.7
macOS
macOS 26.2
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 523.7 | 54.1 | 5.8 GB | view |
| 8k | 563.5 | 49.5 | 6.9 GB | view |
| 16k | 499.6 | 45.4 | 7.6 GB | view |
| 32k | 467.7 | 37.0 | 9.1 GB | view |
| 64k | 310.3 | 14.6 | 12.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.1 | 1.00× |
| 2× | 38.3 | 0.71× |
| 4× | 55.5 | 1.03× |