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

INTELLECT 3 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  INTELLECT 3 4bit   URL Share it on

  14   

INTELLECT 3 4bit is an open-source language model by mlx-community. Features: 106.9b LLM, VRAM: 60.4GB, Context: 128K, License: mit, Quantized, LLM Explorer Score: 0.35, ELO: 1356.

  4-bit   4bit   Agentic Base model:primeintellect/inte... Base model:quantized:primeinte...   Conversational   Custom code   En   Glm4 moe   Mixture-of-experts   Mlx   Prime-intellect   Prime-rl   Quantized   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Verifiers
Model Card on HF 🤗: https://huggingface.co/mlx-community/INTELLECT-3-4bit 

INTELLECT 3 4bit Benchmarks

LMSys ELO: 1356 vs 1272 (so35)6.6%
LLME Score: 0.34965
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
INTELLECT 3 4bit (mlx-community/INTELLECT-3-4bit)
🌟 Advertise your project 🚀

INTELLECT 3 4bit Parameters and Internals

LLM NameINTELLECT 3 4bit
Repository 🤗https://huggingface.co/mlx-community/INTELLECT-3-4bit 
Base Model(s)  INTELLECT 3   PrimeIntellect/INTELLECT-3
Model Size106.9b
Required VRAM60.4 GB
Updated2026-07-18
Maintainermlx-community
Model Typeglm4_moe
Model Files  5.3 GB: 1-of-12   5.3 GB: 2-of-12   5.3 GB: 3-of-12   5.3 GB: 4-of-12   5.3 GB: 5-of-12   5.3 GB: 6-of-12   5.3 GB: 7-of-12   5.3 GB: 8-of-12   5.3 GB: 9-of-12   5.3 GB: 10-of-12   5.3 GB: 11-of-12   2.1 GB: 12-of-12
Supported Languagesen
Quantization Type4bit
Model ArchitectureGlm4MoeForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.56.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size151552

Best Alternatives to INTELLECT 3 4bit

Best Alternatives
Context / RAM
Downloads
Likes
GLM 4.5 Air 2bit128K / 33.4 GB1454
GLM 4.5 Air 8bit128K / 114.1 GB450810
GLM 4.5 Air 3bit128K / 46.6 GB45431
GLM 4.5 Air 6bit128K / 86.7 GB2013
GLM 4.5 Air 3bit DWQ V2128K / 46.6 GB634
GLM 4.5 Air 3bit DWQ128K / 53.3 GB654
GLM 4.5 Air 2bit DWQ128K / 40.2 GB282
INTELLECT 3128K / 194.3 GB2923216
GLM 4.5 Air Mxfp4128K / 56.6 GB832
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/INTELLECT-3-4bit.

Rank the INTELLECT 3 4bit 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? 55269 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