← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-TextoQ4
Performance
1k
tokens
1,642
PP tok/s
290.4
TG tok/s
624
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,642 | 290.4 | 20.7 GB | current |
| 4k | 1,194 | 81.5 | 20.8 GB | view |