← Back to community benchmarks
Qwen3.6-35B-A3B
Performance
16k
tokens
2,050
PP tok/s
56.8
TG tok/s
7993
TTFT (ms)
37.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,374 | 67.2 | 35.4 GB | view |
| 4k | 2,073 | 65.3 | 36.2 GB | view |
| 8k | 2,153 | 62.4 | 36.5 GB | view |
| 16k | 2,050 | 56.8 | 37.1 GB | current |
| 32k | 1,743 | 44.8 | 38.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 67.2 | 1.00× |
| 2× | 103.3 | 1.54× |
| 4× | 136.9 | 2.04× |