What are the hardware requirements for Jan Nano 128K?

Jan Nano 128K requires approximately 8.1 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Jan Nano 128K and how large is it?

Jan Nano 128K is developed by Menlo, 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 Nano 128K?

Jan Nano 128K is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Jan Nano 128K by Menlo — VRAM 8.1GB, 128K context

Name: Jan Nano 128K
Author: Menlo

Jan Nano 128K is an open-source language model by Menlo. Features: 4b LLM, VRAM: 8.1GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.27.

Arxiv:2506.22760 Base model:finetune:menlo/jan-... Base model:menlo/jan-nano Conversational En Endpoints compatible Qwen3 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/Menlo/Jan-nano-128k

Jan Nano 128K Parameters and Internals

LLM Name	Jan Nano 128K
Repository 🤗	https://huggingface.co/Menlo/Jan-nano-128k
Base Model(s)	Jan Nano Menlo/Jan-nano
Model Size	4b
Required VRAM	8.1 GB
Updated	2026-07-21
Maintainer	Menlo
Model Type	qwen3
Model Files	5.0 GB: 1-of-2 3.1 GB: 2-of-2
Supported Languages	en
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.52.4
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Jan Nano 128K 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

Quantized Models of the Jan Nano 128K

Model	Likes	Downloads	VRAM
Jan Nano 128K 4bit	2	26	2 GB

Best Alternatives to Jan Nano 128K

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3 4B Instruct 2507	256K / 8.1 GB	3109972	911
GRPO 4 70	256K / 8.1 GB	13	0
FastContext 1.0 4B SFT	256K / 8.1 GB	5735	357
...2.5 Flash Lite Preview Distill	256K / 8.1 GB	31	1
SRA RiskGate 4B	256K / 8 GB	2662	1
Lightning 4B	256K / 8.1 GB	13	6
Qwen3 4B Thinking 2507	256K / 8.1 GB	291023	606
Mgi Assistant V1 Qwen3 4B	256K / 8.1 GB	669	1
Qwen3 4B Instruct 2507 FP8	256K / 5.2 GB	1100744	78
FastContext 1.0 4B RL	256K / 8.1 GB	4559	61

Note: green Score (e.g. "73.2") means that the model is better than Menlo/Jan-nano-128k.