← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
600.2
PP tok/s
52.6
TG tok/s
6824
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 504.1 | 54.8 | 35.4 GB | view |
| 4k | 600.2 | 52.6 | 36.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.8 | 1.00× |
| 2× | 83.8 | 1.53× |
| 4× | 108.6 | 1.98× |