← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
736.8
PP tok/s
67.5
TG tok/s
22237
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
64 GB
GPU Cores
38
Software
oMLX
v0.3.9
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 572.9 | 62.8 | 19.3 GB | view |
| 4k | 687.2 | 74.4 | 20.0 GB | view |
| 8k | 773.2 | 73.1 | 20.5 GB | view |
| 16k | 736.8 | 67.5 | 21.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.8 | 1.00× |
| 2× | 109.8 | 1.75× |
| 4× | 139.5 | 2.22× |
| 8× | 166.2 | 2.65× |