whatmodel.sh / Infinity-Instruct-3M-0625-Llama3-70B

Infinity-Instruct-3M-0625-Llama3-70B

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

Infinity-Instruct-3M-0625-Llama3-70B is an open-weights language model from BAAI, released July 2024. Its published size is 70.55B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo BAAI/Infinity-Instruct-3M-0625-Llama3-70B @6d8cead: licence tag apache-2.0. 70,553,706,496 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-07: month the maker's Hugging Face repo was created (createdAt 2024-07-09).

49.8±1.6#450 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 Infinity-Instruct-3M-0625-Llama3-70B, out of 1132 with a score, then more from BAAI.

#modelscorewhereRAMreleased
579Bielik 11B v2.3 Instruct SpeakLeash50±2local~8.6GB2024-08
580Qwen2.5-VL 7B Instruct Alibaba50±1local~6.4GB2025-01
581Infinity-Instruct-3M-0625-Llama3-70B BAAI50±2local~29GB2024-07
582Molmo 72B (0924) Ai250±2local~309GB2024-09
583Codestral 22B v0.1 Mistral AI50±1local~15GB2024-05
more from BAAI
490Infinity-Instruct-7M-Gen-Llama3_1-70B BAAI53±2local~27GB2024-07
559Infinity-Instruct-7M-Gen-mistral-7B BAAI50±2local~6.1GB2024-07
631Infinity-Instruct-7M-Gen-Llama3_1-8B BAAI48±2local~6.6GB2024-08

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #280 of 466 * · 99% of its score · 1 test

Beats Ministral 3 14B Reasoning 2512, Ministral 3 14B, OpenThinker2 32B here, though they rank higher overall. Trails Flan-T5 XXL, Granite 4.0 H 1B, Granite 4.0 1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled38.0% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 93/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%at its level

$ 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 Infinity-Instruct-3M-0625-Llama3-70B · needs ~42.5 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/Infinity-Instruct-3M-0625-Llama3-70B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/Infinity-Instruct-3M-0625-Llama3-70B-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 Infinity-Instruct-3M-0625-Llama3-70B · needs ~42.5 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-70B-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 Infinity-Instruct-3M-0625-Llama3-70B · needs ~42.5 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-70B-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~141.11 GB · from huggingface.co/BAAI (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='BAAI/Infinity-Instruct-3M-0625-Llama3-70B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/BAAI ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 99%

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
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 49.8

$ 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