← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
8k
tokens
384.9
PP tok/s
29.3
TG tok/s
21281
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 373.7 | 31.9 | 20.6 GB | view |
| 4k | 398.2 | 30.6 | 21.3 GB | view |
| 8k | 384.9 | 29.3 | 21.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.9 | 1.00× |
| 2× | 52.9 | 1.66× |
| 4× | 70.3 | 2.20× |
| 8× | 80.2 | 2.51× |