whatmodel.sh / Jais Family 1p3b (1.3B) Chat

Jais Family 1p3b (1.3B) Chat

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Jais Family 1p3b (1.3B) Chat is an open-weights language model from Inception (G42), released August 2024. Its published size is 1.56B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo inception42/jais-family-1p3b-chat @4b93176 (requested as inceptionai/jais-family-1p3b-chat, which the HF API redirects to inception42/jais-family-1p3b-chat): licence tag apache-2.0. 1,558,368,784 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-08: month the maker's Hugging Face repo was created (createdAt 2024-08-02). Gated repository (licence acceptance required on Hugging Face).

36.6±4.6#780 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 Jais Family 1p3b (1.3B) Chat, out of 1132 with a score, then more from Inception (G42).

#modelscorewhereRAMreleased
943Qwen1.5 7B Chat Alibaba37±1local~6.5GB2024-02
944Yi 1.5 6B Chat 01.AI37±2local~5.1GB2024-05
945Jais Family 1p3b (1.3B) Chat Inception (G42)37±5local~2.6GB2024-08
946Falcon3 3B Instruct TII37±3local~3.4GB2024-12
947Zephyr 7B alpha Hugging Face36±1local~6.1GB2023-10
more from Inception (G42)
323Jais 2 70B Chat Inception (G42)59±4comparison only2025-12
537Jais 2 8B Chat Inception (G42)51±5comparison only2025-12
713Jais Family 30B 16K Chat Inception (G42)46±3local~131GB2024-08

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #387 of 466 * · 90% of its score · 1 test

Beats OpenThinker3 7B, Gemma 4 E2B, Code Llama 70B Instruct here, though they rank higher overall. Trails Granite 4.0 H 350M, LFM2 350M, Gemma 3 1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arabic IFEval prompt-level (Inception) lab13.6% ✎▁·▁▁▂▁▄▄▆▄█▄ beats 6/38medium · avg 49%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%sharp

$ where to run it

llama.cpp · recommended

version

  1. 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 ↗

  2. Run Jais Family 1p3b (1.3B) Chat · needs ~1 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/jais-family-1p3b-chat-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/jais-family-1p3b-chat-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Jais Family 1p3b (1.3B) Chat · needs ~1 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/jais-family-1p3b-chat-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Jais Family 1p3b (1.3B) Chat · needs ~1 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/jais-family-1p3b-chat-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~6.23 GB · from huggingface.co/inception42 (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='inception42/jais-family-1p3b-chat', torch_dtype='auto', device_map='auto', trust_remote_code=True)('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/inception42 ↗

$ how the score was worked out · Inception Arabic/Hindi leader… 90%

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

sourceresultsshare of the scorelicence
Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval) · lab-reported1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%Apache-2.0
prior · pull toward the middle▇▇▇ 10%
weighted average= 36.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit 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 · sources and licences · json