whatmodel.sh / Pythia 160M

Pythia 160M

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

Pythia 160M is an open-weights language model from EleutherAI, released February 2023. Its published size is 0.162B 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.

2.6±1.7#714 of 719 LLMsfrom 7 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Pythia 160M, out of 828 with a score, then more from EleutherAI.

#modelscorewhereRAMreleased
821OPT-350M Meta5±2local~2.2GB2022-05
822StableLM-Base-Alpha 3B Stability AI4±1local~17GB2023-04
823Pythia 160M EleutherAI3±2local~1.6GB2023-02
824OPT-125M Meta3±2local~1.8GB2022-05
825GPT-2 Large (774M) OpenAI1±2local~2GB2019-08
more from EleutherAI
756GPT-NeoX-20B EleutherAI28±1local~14GB2022-02
777Pythia 12B EleutherAI25±1local~9.5GB2023-02
780GPT-J 6B EleutherAI25±1local~14GB2021-06

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests7 not in a task · 99% of its score
testresultvs the others in its rundifficultycountswhy
SciQ lab74.1% ✎▂··▃▃▂▂▆▃▃█▂ beats 1/19very easy · avg 98%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 35%at its level
ARC Easy lab43.5% ✎▃·▅▃▃▅·██▃██ beats 2/19very easy · avg 90%▇▇▇▇▇▇▇▇▇▇ 25%at its level
LAMBADA (OpenAI version), last-word accuracy lab32.8% ✎▃··▅▃▃▅▅▅███ beats 1/19very easy · avg 89%▇▇▇▇▇▇ 14%blunt · at its level
PIQA lab62.7% ✎▂·▄▄·▄▂▆▂▄█▄ beats 1/19easy · avg 88%▇▇▇▇▇▇ 14%blunt · at its level
WinoGrande lab53.1% ✎▄····▄▆▂▄▆▆█ beats 4/19easy · avg 89%▇▇▇ 7.4%too hard for it
ARC Challenge lab18.8% ✎█··▁·▁▁·▁▂▁▂ beats 8/19medium · avg 72%▇ 2.7%sharp · too hard for it
Open PT-LLM Leaderboard average (9 Portuguese tasks)29.4% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 10/276medium · avg 73%▇ 0.7%too hard for it · noisy

$ 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 Pythia 160M · needs ~0.1 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/pythia-160m-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/pythia-160m-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 Pythia 160M · needs ~0.1 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/pythia-160m-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 Pythia 160M · needs ~0.1 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/pythia-160m-GGUF:Q4_K_M

MLX (Mac)

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Pythia 160M · needs ~0.3 GB, Mac only · from huggingface.co/masahiroid
    chat in the terminal
    mlx_lm.chat --model masahiroid/pythia-160m-mlx
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model masahiroid/pythia-160m-mlx

Other ways to run it

  1. Run it as published · needs ~0.37 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-160m')('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… 98%, Open Portuguese LLM Leaderboa… 1%

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
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling — authors' own runs · lab-reported6▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%CC BY-SA 4.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 2.6

$ 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