← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
4,656
PP tok/s
117.6
TG tok/s
1760
TTFT (ms)
20.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 26.5.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,796 | 123.8 | 19.2 GB | view |
| 4k | 4,765 | 122.7 | 20.0 GB | view |
| 8k | 4,656 | 117.6 | 20.5 GB | current |
| 16k | 4,254 | 110.9 | 21.6 GB | view |
| 32k | 3,526 | 103.1 | 22.7 GB | view |
| 64k | 2,462 | 86.1 | 25.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 123.8 | 1.00× |
| 2× | 215.3 | 1.74× |
| 4× | 333.4 | 2.69× |