← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
1,334
PP tok/s
66.0
TG tok/s
12284
TTFT (ms)
38.9
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,087 | 95.2 | 37.1 GB | view |
| 4k | 1,399 | 90.2 | 37.9 GB | view |
| 8k | 1,434 | 79.9 | 38.2 GB | view |
| 16k | 1,334 | 66.0 | 38.9 GB | current |
| 32k | 1,163 | 48.2 | 40.2 GB | view |
| 64k | 867.1 | 30.8 | 42.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 95.2 | 1.00× |
| 2× | 157.6 | 1.66× |
| 4× | 223.4 | 2.35× |