LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Leaderboards   Agents   Benchmarks    LLM Hosting    Advertise

GLM 4.7 Flash Heretic by Olafangensan

 »  All LLMs  »  Olafangensan  »  GLM 4.7 Flash Heretic   URL Share it on

  512   

GLM 4.7 Flash Heretic is an open-source language model by Olafangensan. Features: 29.9b LLM, VRAM: 59.9GB, Context: 198K, License: mit, MoE, LLM Explorer Score: 0.24.

  Arxiv:2508.06471   Abliterated   Conversational   Decensored   En   Endpoints compatible   Glm4 moe lite   Heretic   Moe   Region:us   Safetensors   Sharded   Tensorflow   Uncensored   Zh
Model Card on HF 🤗: https://huggingface.co/Olafangensan/GLM-4.7-Flash-heretic 

GLM 4.7 Flash Heretic Benchmarks

LLME Score: 0.24211
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GLM 4.7 Flash Heretic (Olafangensan/GLM-4.7-Flash-heretic)

GLM 4.7 Flash Heretic Parameters and Internals

LLM NameGLM 4.7 Flash Heretic
Repository 🤗https://huggingface.co/Olafangensan/GLM-4.7-Flash-heretic 
Model Size29.9b
Required VRAM59.9 GB
Updated2026-07-26
MaintainerOlafangensan
Model Typeglm4_moe_lite
Model Files  49.7 GB: 1-of-2   10.2 GB: 2-of-2
Supported Languagesen zh
Model ArchitectureGlm4MoeLiteForCausalLM
Licensemit
Context Length202752
Model Max Length202752
Transformers Version5.0.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size154880

Best Alternatives to GLM 4.7 Flash Heretic

Best Alternatives
Context / RAM
Downloads
Likes
Glm 4.7 Flash Opus Reasoning198K / 59.9 GB100
...LM 4.7 Flash Abliterated Mxfp8198K / 30.7 GB1722
GLM 4.7 Flash Impotent Heresy198K / 59.9 GB2314
GLM 4.7 Flash 8bit198K / 31.9 GB486324
GLM 4.7 Flash 4bit198K / 17 GB760566
GLM 4.7 Flash 6bit198K / 24.2 GB40537
GLM 4.7 Flash 4bit Mxfp4198K / 15.9 GB2374
....5 High Reasoning Distill 6bit198K / 24.2 GB1972
....5 High Reasoning Distill 4bit198K / 17 GB1912
GLM 4.7 Flash 8bit Gs32198K / 33.6 GB1835
Note: green Score (e.g. "73.2") means that the model is better than Olafangensan/GLM-4.7-Flash-heretic.

Rank the GLM 4.7 Flash Heretic Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 55556 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer