← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
4k
tokens
2,007
PP tok/s
79.4
TG tok/s
2041
TTFT (ms)
26.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 26.5.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,463 | 81.5 | 25.5 GB | view |
| 4k | 2,007 | 79.4 | 26.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 81.5 | 1.00× |
| 2× | 117.3 | 1.44× |
| 4× | 166.4 | 2.04× |