← Back to community benchmarks
Qwen3.6-35B-A3B-UD
Performance
8k
tokens
600.6
PP tok/s
51.0
TG tok/s
13640
TTFT (ms)
21.7
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 491.0 | 57.6 | 20.4 GB | view |
| 4k | 598.5 | 54.3 | 21.2 GB | view |
| 8k | 600.6 | 51.0 | 21.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.6 | 1.00× |
| 2× | 88.3 | 1.53× |
| 4× | 114.1 | 1.98× |