← Back to community benchmarks
Qwen3.6-35B-A3B-4bit-DWQ
Performance
4k
tokens
1,032
PP tok/s
38.5
TG tok/s
3969
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 808.4 | 40.2 | 20.3 GB | view |
| 4k | 1,032 | 38.5 | 21.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 40.2 | 1.00× |
| 2× | 67.4 | 1.68× |
| 4× | 87.6 | 2.18× |