← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
1,396
PP tok/s
97.1
TG tok/s
5867
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,186 | 109.9 | 19.3 GB | view |
| 4k | 1,414 | 104.4 | 20.0 GB | view |
| 8k | 1,396 | 97.1 | 20.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 109.9 | 1.00× |
| 2× | 170.6 | 1.55× |
| 4× | 227.1 | 2.07× |