Pythia 1B

+ contribute

Pythia 1B is an open-weights language model from EleutherAI, released February 2023. Its published size is 1.01B parameters and a 2k-token context window. Licence: apache-2.0.

Catalogue identity notes

Final (step 143000) checkpoint of the standard (non-deduplicated) Pythia model, repo main branch. Total parameter count from the Pythia model card.

14.2±1.1#700 of 719 LLMsfrom 18 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Pythia 1B, out of 828 with a score, then more from EleutherAI.

#	model	score	where	RAM	released
806	OPT-1.3B Meta	16±1	local	~4.3GB	2022-05
807	Gemma 3 270M IT Google	15±4	local	~1.7GB	2025-08
808	Pythia 1B EleutherAI	14±1	local	~2.2GB	2023-02
809	StableLM-Tuned-Alpha 7B Stability AI	14±2	local	~6.9GB	2023-04
810	BLOOM 1.7B BigScience	14±1	local	~3.1GB	2022-07
	more from EleutherAI
756	GPT-NeoX-20B EleutherAI	28±1	local	~14GB	2022-02
777	Pythia 12B EleutherAI	25±1	local	~9.5GB	2023-02
780	GPT-J 6B EleutherAI	25±1	local	~14GB	2021-06

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests13 not in a task · 99% of its score

test	result	vs the others in its run	difficulty	counts	why
SciQ lab +1	84.0% ✎	▂··▂▃▂▂▆▃▃█▂ beats 7/19	very easy · avg 98%	▇▇▇▇▇▇▇▇ 21%	several runs
ARC Easy lab +1	56.9% ✎	▃·▅▃▃▅·██▃██ beats 8/19	very easy · avg 90%	▇▇▇▇▇▇▇▇ 19%	at its level · several runs
WinoGrande lab +1	53.7% ✎	▄····▄▆▂▄▆▆█ beats 5/19	easy · avg 89%	▇▇▇▇▇ 13%	several runs
PIQA lab +1	70.7% ✎	▂·▄▄·▄▂▆▂▄█▄ beats 8/19	easy · avg 88%	▇▇▇▇ 10%	blunt · at its level · several runs
ARC Challenge lab +1	24.4% ✎	█··▁·▁▁·▁▂▁▂ beats 6/19	easy · avg 88%	▇▇▇▇ 10%	sharp · too hard for it · several runs
HellaSwag	44.7% ✎	▃·····▂▂·▂·█ beats 0/8	very easy · avg 92%	▇▇▇ 7.1%	at its level
LAMBADA (OpenAI version), last-word accuracy lab	56.2% ✎	▃··▅▃▃▅▅▅███ beats 9/19	very easy · avg 89%	▇▇ 6.1%	blunt · at its level
OpenBookQA	37.8% ✎	▄·····▄▄▄██▄ beats 0/8	easy · avg 84%	▇▇ 4.6%	typical

5 more tests

test	result	vs the others in its run	difficulty	counts	why
BoolQ	61.8% ✎	█····▃··█▃·▃ beats 2/8	easy · avg 92%	▇▇ 4.4%	typical
MedQA (USMLE, 4 options)	25.6% ✎	▁▃··▄▁▁··▄▃█ beats 1/17	easy · avg 76%	▇ 1.6%	sharp · too hard for it
MedMCQA	31.6% ✎	▂▂··▄▄▂▂·▄██ beats 5/17	medium · avg 68%	▇ 1.6%	too hard for it
PubMedQA	58.2% ✎	▂·▃▆·▄▂▄▄▂█▂ beats 1/17	medium · avg 77%	▇ 0.8%	blunt · at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)	25.2% ✎	▃▁▁▁▁▁▁▁▂█▅▁ beats 9/276	medium · avg 73%	▇ 0.7%	too hard for it · noisy

$ where to run it

llama.cpp · recommended

version

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 Pythia 1B · needs ~0.7 GB · from huggingface.co/mradermacher
chat in the terminal
llama cli -hf mradermacher/pythia-1b-GGUF:Q4_K_M
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf mradermacher/pythia-1b-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 Pythia 1B · needs ~0.7 GB · from huggingface.co/mradermacher
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/mradermacher/pythia-1b-GGUF@Q4_K_M -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run Pythia 1B · needs ~0.7 GB · from huggingface.co/mradermacher
chat in the terminal
ollama run hf.co/mradermacher/pythia-1b-GGUF:Q4_K_M

Other ways to run it

Run it as published · needs ~2.09 GB · from huggingface.co/EleutherAI (official)
uv run --with torch --with 'transformers<5' python -c "from transformers import pipeline; print(pipeline('text-generation', model='EleutherAI/pythia-1b')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/EleutherAI ↗

$ how the score was worked out · Pythia: A Suite for Analyzing… 48%, OLMo: Accelerating the Scienc… 47%, Open Medical-LLM Leaderboard… 4% and 1 more

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
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runs · lab-reported	6	▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 48%	CC BY-SA 4.0
OLMo: Accelerating the Science of Language Models — authors' own runs	8	▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 47%	CC BY 4.0
Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)	3	▇ 4%	Apache-2.0
Open Portuguese LLM Leaderboard (archived)	1	▇ 1%	Apache-2.0
prior · pull toward the middle		▇ 1%
weighted average		= 14.2

$ 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