← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
577.0
PP tok/s
47.9
TG tok/s
28396
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 490.7 | 65.9 | 19.2 GB | view |
| 4k | 596.3 | 62.6 | 20.0 GB | view |
| 8k | 594.6 | 56.7 | 20.4 GB | view |
| 16k | 577.0 | 47.9 | 21.0 GB | current |
| 32k | 525.8 | 37.9 | 22.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 65.9 | 1.00× |
| 2× | 93.0 | 1.41× |
| 4× | 115.8 | 1.76× |
| 8× | 130.9 | 1.99× |