aj9o9 author hub
GLM 5.3 Flash, hand mixed GGUF Two quants, 87 GB and 112 GB, built by assigning every tensor class by hand instead of using a preset. | build | size | bpw | shards | runs on | | | :| :| :| | | AJ IQ3 XXS | 112.40 GB | 2.80 | 3 | 128 GB unified memory, or a 96 GB card with a smal…
Models
7
Downloads
4,769
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.