whatmodel.sh / Functionary Medium v3.1

Functionary Medium v3.1

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

Functionary Medium v3.1 is an open-weights language model from MeetKai, released August 2024. Its published size is 70.55B parameters. Licence: mit.

Catalogue identity notes

Maker repo meetkai/functionary-medium-v3.1 @5c14094: licence tag mit. 70,553,706,496 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-08: month the maker's Hugging Face repo was created (createdAt 2024-08-02).

57.7±6.5#259 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 Functionary Medium v3.1, out of 1132 with a score, then more from MeetKai.

#modelscorewhereRAMreleased
339Qwen3-VL 30B-A3B Instruct Alibaba58±1api $0.35/M +local~21GB2025-09
340Qwen3-VL 8B Thinking Alibaba58±1api $0.66/M +local~6.8GB2025-10
341Functionary Medium v3.1 MeetKai58±7local~29GB2024-08
342calme-2.2-qwen2.5-72b MaziyarPanahi58±4local~33GB2024-09
343Qwen3 32B Alibaba58±0api $0.13/M +local~20GB2025-04
more from MeetKai
487Functionary Small v3.1 MeetKai53±6local~6.6GB2024-07

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▄▄▃▂▁ #213 of 334 * · 81% of its score · 1 test

Beats o1 (2024-12-17), o3-mini, DeepSeek R1 (Jan '25) here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Mellum2 12B-A2.5B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL v362.3% ✎▁▁▁▁▁▃▅█▅▄▁▁ beats 86/114medium · avg 52%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%blunt · 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 Functionary Medium v3.1 · needs ~42.5 GB · from huggingface.co/second-state
    chat in the terminal
    llama cli -hf second-state/functionary-medium-v3.1-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf second-state/functionary-medium-v3.1-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 Functionary Medium v3.1 · needs ~42.5 GB · from huggingface.co/second-state

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/second-state/functionary-medium-v3.1-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 Functionary Medium v3.1 · needs ~42.5 GB · from huggingface.co/second-state
    chat in the terminal
    ollama run hf.co/second-state/functionary-medium-v3.1-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~141.11 GB · from huggingface.co/meetkai (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='meetkai/functionary-medium-v3.1', torch_dtype='auto', device_map='auto', trust_remote_code=True)('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/meetkai ↗

$ how the score was worked out · Berkeley Function Calling Lea… 81%

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
Berkeley Function Calling Leaderboard result archive1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%Apache-2.0
prior · pull toward the middle▇▇▇▇▇▇ 19%
weighted average= 57.7

$ 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