← Back to community benchmarks
Qwen3.6-35B-A3BoQ4
Performance
1k
tokens
627.5
PP tok/s
54.6
TG tok/s
1632
TTFT (ms)
20.1
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.6 | 1.00× |
| 2× | 107.0 | 1.96× |
| 4× | 226.3 | 4.14× |
| 8× | 375.3 | 6.87× |