whatmodel.sh / Llama-3-Nanda-10B-Chat

Llama-3-Nanda-10B-Chat

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

Llama-3-Nanda-10B-Chat is an open-weights language model from MBZUAI & Inception, released October 2024. Licence: llama3.

Catalogue identity notes

Maker repo MBZUAI/Llama-3-Nanda-10B-Chat @96c2ec3: licence tag llama3. Released 2024-10: month the maker's Hugging Face repo was created (createdAt 2024-10-22). Gated repository (licence acceptance required on Hugging Face).

42.4±4.7#660 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 Llama-3-Nanda-10B-Chat, out of 1132 with a score.

#modelscorewhereRAMreleased
817Infinity-Instruct-3M-0625-Yi-1.5-9B BAAI43±2local~7.1GB2024-07
818Aya Vision 32B Cohere42±3api price unknown +local~71GB2025-03
819Llama-3-Nanda-10B-Chat MBZUAI & Inception42±5local~43GB2024-10
820Fanar 1 9B Instruct QCRI42±6local~7.2GB2025-06
821Tulu 2 DPO 70B Ai242±1local~32GB2023-11

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 90% of its score
testresultvs the others in its rundifficultycountswhy
HindiGen-v1 3C3H score (Inception, Claude 3.5 Sonnet judge) lab31.7% ✎▁▁▁▁·▃·█▆█▇▁ beats 4/31medium · avg 48%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%at its level

$ where to run it

Other ways to run it

  1. Run it as published · needs ~39.94 GB · from huggingface.co/MBZUAI (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='MBZUAI/Llama-3-Nanda-10B-Chat', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/MBZUAI ↗

$ 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= 42.4

$ 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