← Back to community benchmarks

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

M4 Max (40c) · 128 GB · 8bit · 2026-05-03
Performance
8k
tokens
1,700
PP tok/s
83.2
TG tok/s
4819
TTFT (ms)
36.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,181 89.5 35.4 GB view
4k 1,691 86.8 36.2 GB view
8k 1,700 83.2 36.5 GB current
Batching Results
Batch Size TG tok/s Speedup
89.5 1.00×
141.7 1.58×
200.7 2.24×
270.2 3.02×