whatmodel.sh / Llama 3.1 8B (base)

Llama 3.1 8B (base)

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

Llama 3.1 8B (base) is an open-weights language model from Meta, released July 2024. Its published size is 8.03B parameters. Licence: llama3.1.

Catalogue identity notes

Maker repo meta-llama/Llama-3.1-8B @d04e592: licence tag llama3.1. 8,030,261,248 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-07: month the maker's Hugging Face repo was created (createdAt 2024-07-14). Pretrained base checkpoint (not an instruct/chat version). Gated repository (licence acceptance required on Hugging Face).

43.6±3.3#474 of 719 LLMsfrom 4 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of Llama 3.1 8B (base), out of 828 with a score, then more from Meta.

#modelscorewhereRAMreleased
561Granite 3.2 8B Instruct IBM44±1local~6.6GB2025-02
562Code Llama 70B Python Meta44±1local~28GB2024-01
563Llama 3.1 8B (base) Meta44±3local~6.2GB2024-07
564LFM2.5 1.2B Instruct Liquid AI44±2local~2.2GB2026-01
565Granite 3.0 8B Instruct IBM43±1local~6.6GB2024-10
more from Meta
24Muse Spark 1.3 Meta77±1api $2.00/M2026-09
40Muse Spark 1.2 Meta75±1api $2.00/M2026-08
43Muse Spark 1.1 Meta75±1api $2.00/M2026-07

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests4 not in a task · 95% of its score
testresultvs the others in its rundifficultycountswhy
Open Persian LLM Leaderboard v2 average (21 tasks)48.5% ✎▂▄▂▃█▄▃▆▃▅▂▂ beats 25/81medium · avg 58%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 43%blunt · at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)65.4% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 116/276medium · avg 73%▇▇▇▇▇▇▇▇▇ 22%at its level · noisy
EuroEval HellaSwag (English), test split, 5-shot generative MC, accuracy46.0% ✎▃·▁▁▂▁▃▅█▇▄▁ beats 23/100medium · avg 68%▇▇▇▇▇▇▇ 17%at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy83.5% ✎▁▁▁▁▁▁▁▂▄█▄▃ beats 89/146easy · avg 83%▇▇▇▇▇▇ 14%at its level · 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 Llama 3.1 8B (base) · needs ~4.9 GB · from huggingface.co/fedric95
    chat in the terminal
    llama cli -hf fedric95/Meta-Llama-3.1-8B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf fedric95/Meta-Llama-3.1-8B-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 Llama 3.1 8B (base) · needs ~4.9 GB · from huggingface.co/fedric95

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/fedric95/Meta-Llama-3.1-8B-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 Llama 3.1 8B (base) · needs ~4.9 GB · from huggingface.co/fedric95
    chat in the terminal
    ollama run hf.co/fedric95/Meta-Llama-3.1-8B-GGUF:Q4_K_M

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Llama 3.1 8B (base) · needs ~4.5 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Meta-Llama-3.1-8B-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Meta-Llama-3.1-8B-4bit

Other ways to run it

  1. Run it as published · needs ~16.06 GB · from huggingface.co/meta-llama
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='meta-llama/Llama-3.1-8B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/meta-llama ↗

$ how the score was worked out · Open Persian LLM Leaderboard… 43%, EuroEval leaderboards (result… 31%, Open Portuguese LLM Leaderboa… 22%

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
Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)1▇▇▇▇▇▇▇▇▇▇▇▇▇ 43%Apache-2.0
EuroEval leaderboards (results collection), English generative leaderboard2▇▇▇▇▇▇▇▇▇ 31%MIT
Open Portuguese LLM Leaderboard (archived)1▇▇▇▇▇▇▇ 22%Apache-2.0
prior · pull toward the middle▇ 5%
weighted average= 43.6

$ 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