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

LongCat Flash Thinking FP8 by meituan-longcat

 »  All LLMs  »  meituan-longcat  »  LongCat Flash Thinking FP8   URL Share it on

  4   

LongCat Flash Thinking FP8 is an open-source language model by meituan-longcat. Features: 561.9b LLM, VRAM: 0.1GB, Context: 128K, License: mit, LLM Explorer Score: 0.22.

  Arxiv:2509.18883   Conversational   Custom code   Fp8   Longcat-flash-chat   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-FP8 

LongCat Flash Thinking FP8 Benchmarks

LLME Score: 0.21702
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LongCat Flash Thinking FP8 (meituan-longcat/LongCat-Flash-Thinking-FP8)
🌟 Advertise your project 🚀

LongCat Flash Thinking FP8 Parameters and Internals

LLM NameLongCat Flash Thinking FP8
Repository 🤗https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-FP8 
Model Size561.9b
Required VRAM0.1 GB
Updated2026-04-18
Maintainermeituan-longcat
Model Files  1.6 GB: 1-of-75   1.8 GB: 2-of-75   0.1 GB: 3-of-75   1.7 GB: 4-of-75   0.1 GB: 5-of-75   16.1 GB: 6-of-75   16.1 GB: 7-of-75   15.9 GB: 8-of-75   16.0 GB: 9-of-75   15.9 GB: 10-of-75   12.1 GB: 11-of-75   12.1 GB: 12-of-75   11.9 GB: 13-of-75   12.0 GB: 14-of-75   12.0 GB: 15-of-75   16.1 GB: 16-of-75   16.1 GB: 17-of-75   15.9 GB: 18-of-75   16.0 GB: 19-of-75   15.9 GB: 20-of-75   12.1 GB: 21-of-75   12.1 GB: 22-of-75   11.9 GB: 23-of-75   12.0 GB: 24-of-75   12.0 GB: 25-of-75   8.2 GB: 26-of-75   8.1 GB: 27-of-75   8.0 GB: 28-of-75   8.1 GB: 29-of-75   8.0 GB: 30-of-75   8.2 GB: 31-of-75   8.1 GB: 32-of-75   8.0 GB: 33-of-75   8.1 GB: 34-of-75   8.0 GB: 35-of-75   8.2 GB: 36-of-75   8.1 GB: 37-of-75   8.0 GB: 38-of-75   8.1 GB: 39-of-75   8.0 GB: 40-of-75   8.2 GB: 41-of-75   8.1 GB: 42-of-75
Model ArchitectureLongcatFlashForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Vocabulary Size131072

Best Alternatives to LongCat Flash Thinking FP8

Best Alternatives
Context / RAM
Downloads
Likes
LongCat Flash Chat128K / 0.1 GB43986530
Note: green Score (e.g. "73.2") means that the model is better than meituan-longcat/LongCat-Flash-Thinking-FP8.

Rank the LongCat Flash Thinking FP8 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? 53089 in total.

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