← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
3,763
PP tok/s
71.7
TG tok/s
1089
TTFT (ms)
66.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.4.2.dev3
macOS
macOS 26.5.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,343 | 73.4 | 65.6 GB | view |
| 4k | 3,763 | 71.7 | 66.4 GB | current |
| 8k | 3,700 | 70.3 | 66.7 GB | view |
| 16k | 3,441 | 68.3 | 67.4 GB | view |
| 32k | 2,968 | 63.8 | 68.7 GB | view |
| 64k | 2,261 | 57.1 | 71.3 GB | view |
| 128k | 1,487 | 34.8 | 76.8 GB | view |
| 195k | 1,082 | 39.9 | 82.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.4 | 1.00× |
| 2× | 66.3 | 0.90× |
| 4× | 133.3 | 1.82× |
| 8× | 267.0 | 3.64× |