← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
98.8
PP tok/s
11.1
TG tok/s
41446
TTFT (ms)
10.1
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.13
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 82.0 | 11.3 | 9.9 GB | view |
| 4k | 98.8 | 11.1 | 10.1 GB | current |