← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
712.1
PP tok/s
59.0
TG tok/s
5752
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 600.4 | 62.1 | 19.2 GB | view |
| 4k | 712.1 | 59.0 | 20.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.1 | 1.00× |
| 2× | 98.6 | 1.59× |
| 4× | 114.8 | 1.85× |