← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6
Performance
64k
tokens
1,772
PP tok/s
57.4
TG tok/s
36994
TTFT (ms)
33.5
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
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,988 | 99.3 | 27.7 GB | view |
| 4k | 2,064 | 93.7 | 28.5 GB | view |
| 8k | 2,360 | 96.6 | 28.9 GB | view |
| 16k | 2,526 | 87.0 | 29.5 GB | view |
| 32k | 2,272 | 75.4 | 30.8 GB | view |
| 64k | 1,772 | 57.4 | 33.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 99.3 | 1.00× |
| 2× | 151.8 | 1.53× |
| 4× | 204.7 | 2.06× |