← Back to community benchmarks

GLM-5-4bit_副本

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-15
Performance
4k
tokens
181.7
PP tok/s
14.1
TG tok/s
22539
TTFT (ms)
394.1
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.12
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 188.1 17.1 391.8 GB view
4k 181.7 14.1 394.1 GB current
8k 155.6 13.7 396.7 GB view
16k 119.7 12.9 402.7 GB view
Batching Results
Batch Size TG tok/s Speedup
17.1 1.00×
24.6 1.44×
31.5 1.84×
44.1 2.58×