What are the hardware requirements for Jan V3 4B Base Instruct?

Jan V3 4B Base Instruct requires approximately 8.9 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Jan V3 4B Base Instruct and how large is it?

Jan V3 4B Base Instruct is developed by janhq, a model with 4b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Jan V3 4B Base Instruct?

Jan V3 4B Base Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Jan V3 4B Base Instruct by janhq — VRAM 8.9GB, 256K context

Name: Jan V3 4B Base Instruct
Author: janhq

Jan V3 4B Base Instruct is an open-source language model by janhq. Features: 4b LLM, VRAM: 8.9GB, Context: 256K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.26.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-4b-instr... Code Conversational En Endpoints compatible Instruct Qwen3 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/janhq/Jan-v3-4B-base-instruct

Jan V3 4B Base Instruct Benchmarks

LLME Score: 0.25639

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Jan V3 4B Base Instruct (janhq/Jan-v3-4B-base-instruct)

🌟 Advertise your project 🚀

Jan V3 4B Base Instruct Parameters and Internals

LLM Name	Jan V3 4B Base Instruct
Repository 🤗	https://huggingface.co/janhq/Jan-v3-4B-base-instruct
Base Model(s)	Qwen3 4B Instruct 2507 Qwen/Qwen3-4B-Instruct-2507
Model Size	4b
Required VRAM	8.9 GB
Updated	2026-05-16
Maintainer	janhq
Model Type	qwen3
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-2 3.9 GB: 2-of-2
Supported Languages	en
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Quantized Models of the Jan V3 4B Base Instruct

Model	Likes	Downloads	VRAM
Jan V3 4B Base Instruct 4bit	2	380	2 GB
Jan V3 4B Base Instruct 8bit	3	51	4 GB

Best Alternatives to Jan V3 4B Base Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3 4B Instruct 2507	256K / 8.1 GB	4833125	869
Qwen3 4B Instruct 2507 FP8	256K / 5.2 GB	840281	79
CyberSecQwen 4B	256K / 8 GB	1216	13
Jan Code 4B	256K / 8.9 GB	417	78
Qwen3 4B Elderly Sft Merged	256K / 8.1 GB	343	0
Qwen3 4B DASD 32K	256K / 8 GB	446	0
SimpleSD 4B Instruct	256K / 8.1 GB	1108	4
Qwen3 4B Instruct 2507	256K / 8.1 GB	41284	26
Jan V3.5 4B	256K / 8.9 GB	457	16
Vector L1 4B	256K / 8.1 GB	9	1

Note: green Score (e.g. "73.2") means that the model is better than janhq/Jan-v3-4B-base-instruct.

Rank the Jan V3 4B Base Instruct 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? 54415 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

Jan V3 4B Base Instruct by janhq