← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-TextoQ4
Performance
1k
tokens
1,638
PP tok/s
275.5
TG tok/s
625
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 | 1,638 | 275.5 | 20.7 GB | current |
| 4k | 1,190 | 81.8 | 20.8 GB | view |