← Back to community benchmarks

Huihui-GLM-4.7-Flash-abliterated

M3 Max (40c) · 128 GB · 4bit · 2026-03-10
User commentvanch test
Performance
1k
tokens
920.5
PP tok/s
67.4
TG tok/s
1112
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.7
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 920.5 67.4 16.4 GB current
4k 931.8 62.0 17.6 GB view
Batching Results
Batch Size TG tok/s Speedup
67.4 1.00×
106.7 1.58×
147.5 2.19×
152.7 2.27×