← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6
Performance
16k
tokens
3,116
PP tok/s
89.3
TG tok/s
5258
TTFT (ms)
29.5
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,993 | 101.5 | 27.7 GB | view |
| 4k | 2,834 | 99.7 | 28.5 GB | view |
| 8k | 3,195 | 93.2 | 28.9 GB | view |
| 16k | 3,116 | 89.3 | 29.5 GB | current |
| 32k | 2,782 | 4.7 | 66.3 GB | view |
| 64k | 1,932 | 25.4 | 68.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 101.5 | 1.00× |
| 2× | 58.9 | 0.58× |
| 4× | 91.0 | 0.90× |