← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
8k
tokens
528.2
PP tok/s
56.3
TG tok/s
15511
TTFT (ms)
19.4
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 502.2 | 63.9 | 18.2 GB | view |
| 4k | 505.8 | 61.3 | 19.0 GB | view |
| 8k | 528.2 | 56.3 | 19.4 GB | current |
| 16k | 524.0 | 46.1 | 20.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 63.9 | 1.00× |
| 2× | 90.2 | 1.41× |
| 4× | 110.4 | 1.73× |
| 8× | 129.6 | 2.03× |