← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
16k
tokens
3,560
PP tok/s
96.6
TG tok/s
4602
TTFT (ms)
22.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,293 | 115.2 | 20.4 GB | view |
| 4k | 3,741 | 110.1 | 21.2 GB | view |
| 8k | 4,023 | 104.7 | 21.5 GB | view |
| 16k | 3,560 | 96.6 | 22.2 GB | current |
| 32k | 2,776 | 70.7 | 23.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 115.2 | 1.00× |
| 2× | 186.0 | 1.61× |
| 4× | 279.5 | 2.43× |