LLM EXPLORER 62,751 MODELS INDEXED

GLM 5.3 Flash JANGH2 by JANGQ-AI

By JANGQ-AI · 296 downloads
HF Repo ↗ Copy URL

GLM 5.3 Flash JANGH2 is an open-source language model by JANGQ-AI. Features: 32.6b LLM, VRAM: 103.6GB, License: mit, LLM Explorer Score: 0.31.

  8-bit   Agent   Apple-silicon Base model:quantized:zai-org/g... Base model:zai-org/glm-5.3-fla...   Conversational   En   Glm5 next   Gptq   Image-text-to-text   Imatrix   Jang   Jangh   Mlx   Moe   Quantized   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Thinking   Tool-use   Video   Vision
Model Card on HF 🤗: https://huggingface.co/JANGQ-AI/GLM-5.3-Flash-JANGH2 

GLM 5.3 Flash JANGH2 Parameters and Internals

LLM NameGLM 5.3 Flash JANGH2
Repository 🤗https://huggingface.co/JANGQ-AI/GLM-5.3-Flash-JANGH2 
Base Model(s)  zai-org/GLM-5.3-Flash   zai-org/GLM-5.3-Flash
Model Size32.6b
Required VRAM103.6 GB
Updated2026-10-02
MaintainerJANGQ-AI
Model Typeglm5_next
Model Files  5.4 GB: 1-of-19   5.9 GB: 2-of-19   5.5 GB: 3-of-19   5.8 GB: 4-of-19   5.5 GB: 5-of-19   5.8 GB: 6-of-19   5.8 GB: 7-of-19   5.5 GB: 8-of-19   5.8 GB: 9-of-19   5.8 GB: 10-of-19   6.0 GB: 11-of-19   5.5 GB: 12-of-19   6.0 GB: 13-of-19   5.8 GB: 14-of-19   5.5 GB: 15-of-19   5.8 GB: 16-of-19   5.8 GB: 17-of-19   5.5 GB: 18-of-19   0.9 GB: 19-of-19
Supported Languagesen
Model ArchitectureGlm5NextForConditionalGeneration
Licensemit
Model Max Length1048576
Transformers Version5.16.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>