CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / Jan-nano
From: Menlo <huggingface.co/Menlo>Newsgroups: alt.freeweights.textSubject:

Jan-nano

Date: 2026-11-15Commit: e411796Signed: 2DC28CC7B26A283B ✓

Text generation model with 4B parameters. Safetensors weights, 8.11 GB in all. Published by Menlo under Apache-2.0.

4B params8.11GBJan-nanosafetensorspermissive
FactsParams4BSize8.11 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get Menlo/Jan-nano
# manifest sha256 a234b1436003… · 8.11 GB · 15 files
$ fw verify ./Jan-nano Menlo/Jan-nano
From sourceHosted (signed)Menlo/Jan-nanoLast check: 2026-11-15 03:43 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of Qwen3-4B.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
8.11 GB
Weights
8.04 GB (safetensors)
Parameters
4B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
15, each with a sha256
Publisher
Menlo
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-4B

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 03:43 UTCpassed

Model card

From the publisher at commit e411796. Shown as plain text with links; images open at the publisher.

Jan-Nano: An Agentic Model#

Note: Jan-Nano is a non-thinking model.

GitHub

Image: Jan-Nano

Authors: Alan Dao, Bach Vu Dinh

Overview#

Jan-Nano is a compact 4-billion parameter language model specifically designed and trained for deep research tasks. This model has been optimized to work seamlessly with Model Context Protocol (MCP) servers, enabling efficient integration with various research tools and data sources.

Evaluation#

Jan-Nano has been evaluated on the SimpleQA benchmark using our MCP-based benchmark methodology, demonstrating strong performance for its model size:

Image: image/png

The evaluation was conducted using our MCP-based benchmark approach, which assesses the model's performance on SimpleQA tasks while leveraging its native MCP server integration capabilities. This methodology better reflects Jan-Nano's real-world performance as a tool-augmented research model, validating both its factual accuracy and its effectiveness in MCP-enabled environments.

How to Run Locally#

Image: Jan-Nano Demo

Jan-Nano is currently supported by Jan, an open-source ChatGPT alternative that runs entirely on your computer. Jan provides a user-friendly interface for running local AI models with full privacy and control.

For non-jan app or tutorials there are guidance inside community section, please check those out! Discussion

VLLM#

Here is an example command you can use to run vllm with Jan-nano

vllm serve Menlo/Jan-nano --host 0.0.0.0 --port 1234 --enable-auto-tool-choice --tool-call-parser hermes --chat-template ./qwen3_nonthinking.jinja

Chat-template is already included in tokenizer so chat-template is optional, but in case it has issue you can download the template here Non-think chat template

  • Temperature: 0.7
  • Top-p: 0.8
  • Top-k: 20
  • Min-p: 0

📄 Citation#

@misc{dao2025jannanotechnicalreport,
      title={Jan-nano Technical Report}, 
      author={Alan Dao and Dinh Bach Vu},
      year={2025},
      eprint={2506.22760},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2506.22760}, 
}
Documentation#

Setup, Usage & FAQ

Files

15 files · 8.11 GBWeights 8.04 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 15 files with their sha256
FileSizesha256
.gitattributes1.73 KB4976f0b6678e3b966418f6bf92a017fceb63f28df8f7a0f90c6ad8aa735d5fa8
README.md3.04 KBbf9cdeecdcb78f57045017ce9b243d7c62951dd631f34c1619f0dc219250b595
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
config.json727 Bdf0eb69850f5e26d330ccd5a08d0a19626d8b09d70acafe619dab047f1bcbc78
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00002.safetensors4.97 GBa2bc3d02bcb8683017365f4671d7444ec53ee2739cacb36de96237e8ec87a953
model-00002-of-00002.safetensors3.08 GB811f0ed71ac62d1f7e4361a67b702f45ab7543b8f14b57367828581fc4c531e1
model.safetensors.index.json32.8 KBe36bba5af4706cfd22ecf7eedb5fd8f4d2559b92f2414b932651b9ed6495921a
replay.gif23.2 MBec0e0df1e6f3f96e5f02df181b5eea6dc6f34675a507cabfdddef47eedb0f43c
replay.mp426.7 MB43588ba67463437872071bd69d92657e616daa430c77270b3cfaaeb06781f211
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MB67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
tokenizer_config.json9.76 KB9408b7b287f1237217a2574bc36cc89b254383e105580ee32dcbea949886db6e
training_args.bin7.86 KB8540b312a7fc504b25eb7a85a88f07dd0a50528bfcde454aca0fe0369fe88364
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e411796d1b pinned now2026-11-15 03:43 UTC15 files · 8.11 GB

Use it

$ fw get Menlo/Jan-nano
# manifest sha256 a234b1436003… · 8.11 GB · 15 files
$ fw verify ./Jan-nano Menlo/Jan-nano
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/Menlo/Jan-nano.json --dir ./Jan-nano $ python3 fw.py verify ./Jan-nano ./Menlo__Jan-nano.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Menlo/Jan-nano --revision e411796d1b1c46abb405eeda93e93c8c7e4474e4 --local-dir ./Jan-nano
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("Menlo/Jan-nano", revision="e411796d1b1c46abb405eeda93e93c8c7e4474e4") model = AutoModelForCausalLM.from_pretrained("Menlo/Jan-nano", revision="e411796d1b1c46abb405eeda93e93c8c7e4474e4", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve Menlo/Jan-nano --revision e411796d1b1c46abb405eeda93e93c8c7e4474e4
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
bf9cdeecdcb78f57045017ce9b243d7c62951dd631f34c1619f0dc219250b595
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: Menlo <huggingface.co/Menlo>Newsgroups: alt.freeweights.textSubject: Jan-nanoDate: 2026-11-15Commit: e411796Signed: 2DC28CC7B26A283B ✓
Upstream
Menlo/Jan-nano
Pinned commit
e411796d1b1c46abb405eeda93e93c8c7e4474e4
Manifest
Jan-nano.json · .minisig
Manifest sha256
a234b143600331e1b22905e66a2c479349a3ec63e70d3609f6ecbfc67baeda8d
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:43 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/Menlo/Jan-nano.json $ curl -O https://freeweights.allternit.com/manifests/Menlo/Jan-nano.json.minisig $ minisign -Vm Jan-nano.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

Qwen/Qwen3-4B · this model is a finetune of it

3 models in the catalog name this one as their parent.

Fine-tunes
1
Quantizations
2
Fine-tunes 1
Quantizations 2
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download Menlo/Jan-nano
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Jan-nano.json. Provenance. Takedown history: none.
Source
huggingface.co/Menlo/Jan-nano

Variants

2 quantized or adapter builds of Jan-nano. Each has its own license check and page.

SubjectSizeParamsLicenseDate
Jan-nano-GGUFHosted (signed) From: unsloth in alt.freeweights.text67.8 GB—Permissive2026-11-15Jan-nano-ONNXHosted (signed) From: onnx-community in alt.freeweights.text10.9 GB—Permissive2026-11-15

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B