← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
4k
tokens
565.8
PP tok/s
51.3
TG tok/s
7239
TTFT (ms)
28.1
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
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 461.5 | 53.5 | 27.3 GB | view |
| 4k | 565.8 | 51.3 | 28.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.5 | 1.00× |
| 2× | 74.8 | 1.40× |
| 4× | 89.8 | 1.68× |