← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
1k
tokens
667.3
PP tok/s
37.4
TG tok/s
1535
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8rc1
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 667.3 | 37.4 | 20.4 GB | current |
| 4k | 942.5 | 35.4 | 21.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 37.4 | 1.00× |
| 2× | 58.3 | 1.56× |
| 4× | 84.3 | 2.25× |