Jan v1 4B

+ contribute

Jan v1 4B is an open-weights language model from Jan (Menlo Research), released August 2025. Its published size is 4.02B parameters. Licence: apache-2.0.

Catalogue identity notes

janhq/Jan-v1-4B @3a6fedb (created 2025-08-08, licence apache-2.0). Jan's agentic 4B model (Aug 2025, Qwen3-4B-Thinking based). Independent row: Open PT-LLM leaderboard average.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 4,022,468,096 parameters.

51.5±6.6#404 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Jan v1 4B, out of 1132 with a score.

#	model	score	where	RAM	released
529	Gemini Experimental 1121 Google	52±2	comparison only		2024-11
530	Codestral (25.01) Mistral	52±3	comparison only		2025-01
531	Jan v1 4B Jan (Menlo Research)	52±7	local	~3.9GB	2025-08
532	Cogito v1 Preview Llama 8B Deep Cogito	51±5	local	~6.2GB	2025-03
533	Llama-3-70B-UltraMedical Tsinghua C3I	51±5	local	~29GB	2024-09

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 81% of its score

test	result	vs the others in its run	difficulty	counts	why
Open PT-LLM Leaderboard average (9 Portuguese tasks)	75.2% ✎	▃▁▁▁▁▁▁▁▂█▅▁ beats 226/276	medium · avg 73%	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%	at its level · noisy

$ where to run it

llama.cpp · recommended

Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
macOS / Linux
curl -LsSf https://llama.app/install.sh | sh
Windows
irm https://llama.app/install.ps1 | iex
other ways to install ↗
Run Jan v1 4B · needs ~2.5 GB · from huggingface.co/janhq (official)
chat in the terminal
llama cli -hf janhq/Jan-v1-4B-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf janhq/Jan-v1-4B-GGUF:Q4_K_M

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run Jan v1 4B · needs ~2.5 GB · from huggingface.co/janhq (official)
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/janhq/Jan-v1-4B-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run Jan v1 4B · needs ~2.5 GB · from huggingface.co/janhq (official)
chat in the terminal
ollama run hf.co/janhq/Jan-v1-4B-GGUF:Q4_K_M

MLX (Mac)

version

Install MLX (Mac) · Apple silicon Macs only, text only.
with uv
uv tool install mlx-lm
or
pip install mlx-lm
Run Jan v1 4B · needs ~2.3 GB, Mac only · from huggingface.co/mlx-community
chat in the terminal
mlx_lm.chat --model mlx-community/Jan-v1-4B-4bit
Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/Jan-v1-4B-4bit

Official weights and documentation: huggingface.co/janhq ↗

$ how the score was worked out · Open Portuguese LLM Leaderboa… 81%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
Open Portuguese LLM Leaderboard (archived)	1	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%	Apache-2.0
prior · pull toward the middle		▇▇▇▇▇▇ 19%
weighted average		= 51.5

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated 2026-10-11 02:20 UTC · sources and licences · json