← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
1k
tokens
2,351
PP tok/s
117.0
TG tok/s
436
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,351 | 117.0 | 20.4 GB | current |
| 4k | 3,038 | 112.9 | 21.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 117.0 | 1.00× |
| 2× | 183.1 | 1.56× |
| 4× | 276.8 | 2.37× |
| 8× | 369.6 | 3.16× |