← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
1k
tokens
230.7
PP tok/s
38.8
TG tok/s
4439
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip
M1 Pro (14c)
Memory
32 GB
GPU Cores
14
Software
oMLX
v0.3.6
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 230.7 | 38.8 | 16.4 GB | current |
| 4k | 267.1 | 31.9 | 17.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.8 | 1.00× |
| 2× | 78.7 | 2.03× |
| 4× | 156.1 | 4.02× |