← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
1k
tokens
1,071
PP tok/s
98.7
TG tok/s
956
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 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 | 1,071 | 98.7 | 20.4 GB | current |
| 4k | 1,656 | 95.3 | 21.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 98.7 | 1.00× |
| 2× | 164.1 | 1.66× |
| 4× | 236.1 | 2.39× |