whatmodel.sh / Jais Family 30B 16K Chat

Jais Family 30B 16K Chat

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

Jais Family 30B 16K Chat is an open-weights language model from Inception (G42), released August 2024. Its published size is 30.82B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo inception42/jais-family-30b-16k-chat @369f88e (requested as inceptionai/jais-family-30b-16k-chat, which the HF API redirects to inception42/jais-family-30b-16k-chat): licence tag apache-2.0. 30,817,712,120 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).

45.8±3.0#566 of 949 LLMsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Jais Family 30B 16K Chat, out of 1132 with a score, then more from Inception (G42).

#modelscorewhereRAMreleased
711WizardCoder Python 34B V1.0 WizardLM46±1local~23GB2023-08
712PLLuM-12B-nc-instruct (2412) PLLuM consortium (CYFRAGOVPL)46±4local~8.7GB2025-02
713Jais Family 30B 16K Chat Inception (G42)46±3local~131GB2024-08
714Gemini 1.0 Pro (001) Google46±2comparison only2023-12
715Mistral Medium (2312) Mistral46±1comparison only2023-12
more from Inception (G42)
323Jais 2 70B Chat Inception (G42)59±4comparison only2025-12
537Jais 2 8B Chat Inception (G42)51±5comparison only2025-12
727Jais Family 30B 8K Chat Inception (G42)45±3local~131GB2024-08

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #327 of 466 * · 65% of its score · 1 test

Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, OpenThinker3 7B here, though they rank higher overall. Trails Flan-T5 XXL, LFM2 700M, EXAONE 3.5 2.4B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arabic IFEval prompt-level (Inception) lab29.0% ✎▁·▁▁▂▁▄▄▆▄█▄ beats 16/38medium · avg 49%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 65%sharp · at its level
other tests1 not in a task · 31% of its score
testresultvs the others in its rundifficultycountswhy
AraGen-v3 3C3H score (Inception, Claude Sonnet 4 judge) lab32.3% ✎▁▁·▁▂▂▄█▄▅▄▄ beats 30/66hard · avg 31%▇▇▇▇▇▇▇▇▇▇▇▇ 31%typical

$ where to run it

Other ways to run it

  1. Run it as published · needs ~123.27 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-30b-16k-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… 96%

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-reported2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%Apache-2.0
prior · pull toward the middle▇ 4%
weighted average= 45.8

$ 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