← Back to community benchmarks

Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated

M5 Max (40c) · 128 GB · 8bit · 2026-05-18
Performance
16k
tokens
3,872
PP tok/s
92.4
TG tok/s
4231
TTFT (ms)
37.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,193 98.3 35.4 GB view
4k 3,705 95.7 36.2 GB view
8k 3,967 92.6 36.7 GB view
16k 3,872 92.4 37.4 GB current
32k 3,280 84.4 38.9 GB view
64k 2,226 70.9 41.9 GB view
Batching Results
Batch Size TG tok/s Speedup
98.3 1.00×
155.9 1.59×
231.8 2.36×
307.9 3.13×