← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
16k
tokens
1,357
PP tok/s
77.4
TG tok/s
12075
TTFT (ms)
22.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 15.7.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,323 | 99.3 | 20.4 GB | view |
| 4k | 1,679 | 93.3 | 21.2 GB | view |
| 8k | 1,630 | 87.3 | 21.5 GB | view |
| 16k | 1,357 | 77.4 | 22.2 GB | current |
| 32k | 1,145 | 55.1 | 23.5 GB | view |
| 64k | 876.3 | 37.8 | 26.2 GB | view |
| 128k | 546.1 | 23.9 | 31.6 GB | view |
| 195k | 396.1 | 14.3 | 37.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 99.3 | 1.00× |
| 2× | 156.6 | 1.58× |
| 4× | 231.9 | 2.34× |
| 8× | 279.0 | 2.81× |