← Back to community benchmarks
Qwen3.6-35B-A3B-4bit-DWQ
Performance
1k
tokens
1,166
PP tok/s
76.7
TG tok/s
879
TTFT (ms)
20.3
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,166 | 76.7 | 20.3 GB | current |
| 4k | 2,020 | 70.0 | 21.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 76.7 | 1.00× |
| 2× | 117.6 | 1.53× |
| 4× | 170.7 | 2.23× |