← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
4k
tokens
1,454
PP tok/s
76.6
TG tok/s
2818
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,082 | 80.1 | 20.4 GB | view |
| 4k | 1,454 | 76.6 | 21.2 GB | current |
| 8k | 1,463 | 71.7 | 21.5 GB | view |
| 16k | 1,362 | 60.5 | 22.2 GB | view |
| 32k | 1,084 | 50.1 | 23.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 80.1 | 1.00× |
| 2× | 132.9 | 1.66× |
| 4× | 199.2 | 2.49× |