← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
1,450
PP tok/s
100.2
TG tok/s
2824
TTFT (ms)
19.0
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,146 | 103.3 | 18.3 GB | view |
| 4k | 1,450 | 100.2 | 19.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 103.3 | 1.00× |
| 2× | 167.1 | 1.62× |
| 4× | 236.8 | 2.29× |