← Back to community benchmarks

KyleHessling1-Qwopus-GLM-18B-Healed

M3 Max (40c) · 64 GB · 4bit · 2026-05-04
Performance
1k
tokens
354.8
PP tok/s
37.3
TG tok/s
2886
TTFT (ms)
9.9
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 354.8 37.3 9.9 GB current
4k 374.0 36.4 11.0 GB view
Batching Results
Batch Size TG tok/s Speedup
37.3 1.00×
56.3 1.51×
131.6 3.53×