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

Phi 3.5 MoE Instruct 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Phi 3.5 MoE Instruct 4bit   URL Share it on

  305   

Phi 3.5 MoE Instruct 4bit is an open-source language model by mlx-community. Features: 6.5b LLM, VRAM: 23.7GB, Context: 128K, License: mit, MoE, Quantized, Instruction-Based, LLM Explorer Score: 0.16.

  4bit   Code   Conversational   Custom code   Instruct   Mlx   Moe   Multilingual   Phimoe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Phi-3.5-MoE-instruct-4bit 

Phi 3.5 MoE Instruct 4bit Benchmarks

LLME Score: 0.15762
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 3.5 MoE Instruct 4bit (mlx-community/Phi-3.5-MoE-instruct-4bit)
🌟 Advertise your project 🚀

Phi 3.5 MoE Instruct 4bit Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
nlp, code, mlx
Additional Notes 
The model was converted to MLX format using mlx-lm version 0.17.1.
Supported Languages 
multilingual ()
LLM NamePhi 3.5 MoE Instruct 4bit
Repository 🤗https://huggingface.co/mlx-community/Phi-3.5-MoE-instruct-4bit 
Model Size6.5b
Required VRAM23.7 GB
Updated2026-04-11
Maintainermlx-community
Model Typephimoe
Instruction-BasedYes
Model Files  5.2 GB: 1-of-5   5.4 GB: 2-of-5   5.4 GB: 3-of-5   5.4 GB: 4-of-5   2.3 GB: 5-of-5
Quantization Type4bit
Model ArchitecturePhiMoEForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.43.3
Tokenizer ClassLlamaTokenizer
Padding Token<|end|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi 3.5 MoE Instruct 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 MoE Instruct 8bit128K / 44.5 GB413
Phi 3.5 MoE Instruct128K / 83.9 GB102421572
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Phi-3.5-MoE-instruct-4bit.

Rank the Phi 3.5 MoE Instruct 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? 52721 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