← Back to community benchmarks
Qwen3.6-35B-A3B-oQ6
Performance
4k
tokens
939.1
PP tok/s
56.6
TG tok/s
4362
TTFT (ms)
28.4
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 695.4 | 58.1 | 27.6 GB | view |
| 4k | 939.1 | 56.6 | 28.4 GB | current |
| 8k | 772.5 | 53.5 | 28.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 58.1 | 1.00× |
| 2× | 81.4 | 1.40× |
| 4× | 101.5 | 1.75× |
| 8× | 242.5 | 4.17× |