← Back to community benchmarks

GLM-4.7-Flash-Derestricted-8bit-gs32

M5 Max (40c) · 128 GB · 8bit · 2026-04-24
Performance
4k
tokens
2,375
PP tok/s
64.1
TG tok/s
1725
TTFT (ms)
33.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,138 69.1 32.0 GB view
4k 2,375 64.1 33.0 GB current
Batching Results
Batch Size TG tok/s Speedup
69.1 1.00×
113.8 1.65×
152.6 2.21×