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

Jan V1 4B 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  Jan V1 4B 8bit   URL Share it on

  29   

Jan V1 4B 8bit is an open-source language model by mlx-community. Features: 4b LLM, VRAM: 4.3GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.2.

  8-bit   8bit   Base model:janhq/jan-v1-4b Base model:quantized:janhq/jan...   Conversational   En   Mlx   Quantized   Qwen3   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/mlx-community/Jan-v1-4B-8bit 

Jan V1 4B 8bit Benchmarks

LLME Score: 0.1975
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jan V1 4B 8bit (mlx-community/Jan-v1-4B-8bit)

Jan V1 4B 8bit Parameters and Internals

LLM NameJan V1 4B 8bit
Repository 🤗https://huggingface.co/mlx-community/Jan-v1-4B-8bit 
Base Model(s)  Jan V1 4B   janhq/Jan-v1-4B
Model Size4b
Required VRAM4.3 GB
Updated2026-06-22
Maintainermlx-community
Model Typeqwen3
Model Files  4.3 GB
Supported Languagesen
Quantization Type8bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.52.4
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Jan V1 4B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4b Merged Txt256K / 8.1 GB3920
...Instruct 2507 Unsloth Bnb 4bit256K / 3.5 GB15596214
...wen 3 4b Mythos Finetune 16bit256K / 8.1 GB920
...wen3 4B Thinking 2507 MLX 4bit256K / 2.3 GB5099414
...wen3 4B Thinking 2507 MLX 8bit256K / 4.3 GB447318
EduMentor Qwen3 4B FP16256K / 8.1 GB751
Qwen3 4B Instruct 2507 4bit256K / 2.3 GB3592610
Qwen Finetune 4bit256K / 8.1 GB610
Qwen3 4B INST Code256K / 8.1 GB120
Qwen3 4B INST Math256K / 8.1 GB110
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Jan-v1-4B-8bit.

Rank the Jan V1 4B 8bit 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? 55396 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