whatmodel.sh / Falcon-RW 1B

Falcon-RW 1B

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

Falcon-RW 1B is an open-weights language model from TII, released April 2023. Its published size is 1.3B parameters and a 2k-token context window. Licence: apache-2.0.

Catalogue identity notes

Falcon-RW-1B, 1.3B-parameter model trained on 350B tokens of RefinedWeb only (the phi-1.5 paper labels it 'Falcon-rw-1.3B').

20.1±1.6#691 of 719 LLMsfrom 12 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Falcon-RW 1B, out of 828 with a score, then more from TII.

#modelscorewhereRAMreleased
795Pythia 2.8B (deduped) EleutherAI20±1local~3.4GB2023-02
796Flan-T5 Base Google20±3local~2.5GB2022-10
797Falcon-RW 1B TII20±2local~4.3GB2023-04
798OPT-2.7B Meta19±1local~7.1GB2022-05
799SmolLM2 360M Instruct Hugging Face19±3local~1.7GB2024-10
more from TII
233Falcon-H1R 7B TII60±1local~6GB2026-01
332Falcon-H1 34B Instruct TII54±3local~23GB2025-05
494Falcon-H1 7B Instruct TII46±3local~6GB2025-05

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests12 not in a task · 99% of its score
testresultvs the others in its rundifficultycountswhy
BoolQ63.2% ✎▄█▄···▄··█▄▄ beats 3/8easy · avg 92%▇▇▇▇▇▇ 14%at its level
WinoGrande60.7% ✎█··█···█▄▄·▄ beats 2/8easy · avg 90%▇▇▇▇▇▇ 14%typical
Natural Questions (closed book)9.3% ✎▁·▁·▁▂▁▃·▅▂█ beats 9/28medium · avg 58%▇▇▇▇▇▇ 14%typical
ARC Challenge28.2% ✎▅····▃▃···▅█ beats 3/8easy · avg 79%▇▇▇▇▇ 13%sharp · too hard for it
ARC Easy63.3% ✎▅·▃▃··▃··▃·█ beats 3/8very easy · avg 90%▇▇▇▇▇ 11%at its level
HellaSwag46.6% ✎▃▃▃··▅····▃█ beats 3/8easy · avg 83%▇▇▇▇ 11%at its level
PIQA74.7% ✎▄▄··▄·▄·▄·██ beats 3/8easy · avg 88%▇▇▇ 6.3%blunt · at its level
Social IQA40.5% ✎█▄····█▄▄··▄ beats 2/7medium · avg 63%▇▇ 5.8%blunt
4 more tests
testresultvs the others in its rundifficultycountswhy
OpenBookQA24.4% ✎█······▂·▆·▂ beats 3/8medium · avg 54%▇▇ 4.1%too hard for it · noisy
TriviaQA31.4% ✎▁··▁█▃▃▁▄▅▄█ beats 13/28easy · avg 79%▇ 2.8%noisy
TruthfulQA MC236.0% ✎▅▃█▆▁▂▅···▁▁ beats 4/31medium · avg 64%▇ 1.8%blunt · at its level
HaluEval QA hallucination detection (accuracy)42.2% ✎█▁▁·▁▁·▁▁▁▁▁ beats 0/27medium · avg 70%▇ 0.5%sharp · too hard for it · noisy

$ where to run it

Other ways to run it

  1. Run it as published · needs ~2.62 GB · from huggingface.co/tiiuae (official)
    uv run --with torch --with 'transformers<5' python -c "from transformers import pipeline; print(pipeline('text-generation', model='tiiuae/falcon-rw-1b')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/tiiuae ↗

$ how the score was worked out · Textbooks Are All You Need II… 80%, Hallucinations Leaderboard re… 19%

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
Textbooks Are All You Need II: phi-1.5 technical report — authors' own runs8▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 80%CC BY 4.0
Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)4▇▇▇▇▇▇ 19%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 20.1

$ 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