← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6
Performance
8k
tokens
578.8
PP tok/s
47.0
TG tok/s
14154
TTFT (ms)
28.9
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 454.5 | 51.9 | 27.7 GB | view |
| 4k | 574.9 | 49.6 | 28.5 GB | view |
| 8k | 578.8 | 47.0 | 28.9 GB | current |
| 16k | 558.7 | 42.2 | 29.5 GB | view |
| 32k | 510.8 | 31.7 | 30.8 GB | view |
| 64k | 411.1 | 19.6 | 33.5 GB | view |
| 128k | 261.1 | 9.8 | 38.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.9 | 1.00× |
| 2× | 76.8 | 1.48× |