What are the hardware requirements for Jan V3.5 4B?

Jan V3.5 4B 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 V3.5 4B and how large is it?

Jan V3.5 4B 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 V3.5 4B?

Jan V3.5 4B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Jan V3.5 4B by janhq — VRAM 8.9GB, 256K context

Name: Jan V3.5 4B
Author: janhq

Jan V3.5 4B 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: 0.24.

Base model:finetune:janhq/jan-... Base model:janhq/jan-v3-4b-bas... Conversational En Endpoints compatible Identity Instruct Math Qwen3 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/janhq/Jan-v3.5-4B

Jan V3.5 4B Parameters and Internals

LLM Name	Jan V3.5 4B
Repository 🤗	https://huggingface.co/janhq/Jan-v3.5-4B
Base Model(s)	Jan V3 4B Base Instruct janhq/Jan-v3-4B-base-instruct
Model Size	4b
Required VRAM	8.9 GB
Updated	2026-08-05
Maintainer	janhq
Model Type	qwen3
Instruction-Based	Yes
Model Files	4.7 GB: 1-of-2 4.2 GB: 2-of-2
Supported Languages	en
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	4.57.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the Jan V3.5 4B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Jan V3.5 4B

Best Alternatives	Context / RAM	Downloads	Likes
FastContext 1.0 4B SFT	256K / 8.1 GB	5735	357
Qwen3 4B Instruct 2507	256K / 8.1 GB	3109972	911
Fable Traces	256K / 8.1 GB	295	210
FastContext 1.0 4B RL	256K / 8.1 GB	4559	61
Qwen3 4B Instruct 2507 FP8	256K / 5.2 GB	1100744	78
...pt Full Qwen3 4b Instruct 2507	256K / 8 GB	365	1
Nexa AI 4B Instruct	256K / 8 GB	576	2
Neuron 4B Instruct	256K / 8.1 GB	313	1
Agents K1	256K / 8.8 GB	1098	28
FastContext 1.0 4B SFT	256K / 8.1 GB	273	18

Note: green Score (e.g. "73.2") means that the model is better than janhq/Jan-v3.5-4B.