← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
1k
tokens
879.3
PP tok/s
44.9
TG tok/s
1165
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 879.3 | 44.9 | 16.4 GB | current |
| 4k | 1,111 | 44.5 | 17.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.9 | 1.00× |
| 2× | 76.4 | 1.70× |
| 4× | 98.5 | 2.19× |