← Back to community benchmarks
Qwen3.6-35B-A3B-4bit-DWQ
Performance
32k
tokens
797.9
PP tok/s
48.4
TG tok/s
41067
TTFT (ms)
23.4
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 740.8 | 79.8 | 20.3 GB | view |
| 4k | 959.1 | 68.8 | 21.1 GB | view |
| 8k | 965.8 | 62.3 | 21.5 GB | view |
| 16k | 960.6 | 52.5 | 22.1 GB | view |
| 32k | 797.9 | 48.4 | 23.4 GB | current |
| 64k | 363.0 | 12.5 | 26.1 GB | view |
| 128k | 212.4 | 13.4 | 31.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 79.8 | 1.00× |
| 2× | 74.2 | 0.93× |
| 4× | 101.0 | 1.27× |