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

Jan V3 4B Base Instruct 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Jan V3 4B Base Instruct 4bit   URL Share it on

  541   

Jan V3 4B Base Instruct 4bit is an open-source language model by mlx-community. Features: 4b LLM, VRAM: 2.3GB, Context: 256K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.26.

  4-bit   4bit Base model:janhq/jan-v3-4b-bas... Base model:quantized:janhq/jan...   Code   Conversational   En   Instruct   Mlx   Quantized   Qwen3   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/Jan-v3-4B-base-instruct-4bit 

Jan V3 4B Base Instruct 4bit Benchmarks

LLME Score: 0.25988
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jan V3 4B Base Instruct 4bit (mlx-community/Jan-v3-4B-base-instruct-4bit)
🌟 Advertise your project 🚀

Jan V3 4B Base Instruct 4bit Parameters and Internals

LLM NameJan V3 4B Base Instruct 4bit
Repository 🤗https://huggingface.co/mlx-community/Jan-v3-4B-base-instruct-4bit 
Base Model(s)  Jan V3 4B Base Instruct   janhq/Jan-v3-4B-base-instruct
Model Size4b
Required VRAM2.3 GB
Updated2026-05-02
Maintainermlx-community
Model Typeqwen3
Instruction-BasedYes
Model Files  2.3 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Jan V3 4B Base Instruct 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Agent 4b256K / 8.1 GB3620
...Instruct 2507 Unsloth Bnb 4bit256K / 3.5 GB9555414
...Instruct Haiku 4.5 Merged FP16256K / 8.1 GB300
Qwen3 4B Instruct 2507 4bit256K / 2.3 GB157619
...wen3 4B Instruct 2507 Bnb 4bit256K / 2.6 GB75645
Fact Extractor Dev 1b256K / 8.1 GB410
Jan V3 4B Base Instruct 8bit256K / 4.3 GB733
...4B Instruct 2507 4bit DWQ 2510256K / 2.3 GB1962
Qwen3 4B Instruct 2507 8bit256K / 4.3 GB1324
...wen3 4B Instruct 2507 Sft Full256K / 8.1 GB50
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Jan-v3-4B-base-instruct-4bit.

Rank the Jan V3 4B Base 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? 53701 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