← Back to community benchmarks
Qwen3.6-35B-A3B-oQ4
Performance
4k
tokens
644.6
PP tok/s
76.2
TG tok/s
6355
TTFT (ms)
68.8
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.3.8
macOS
macOS 14.8.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 951.1 | 189.1 | 69.3 GB | view |
| 4k | 644.6 | 76.2 | 68.8 GB | current |