whatmodel.sh / watt-tool-8B

watt-tool-8B

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

watt-tool-8B is an open-weights language model from Watt AI, released December 2024. Its published size is 8.03B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo watt-ai/watt-tool-8B @e966e34: licence tag apache-2.0. 8,030,261,248 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-12: month the maker's Hugging Face repo was created (createdAt 2024-12-19).

62.0±6.6#192 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 watt-tool-8B, out of 1132 with a score, then more from Watt AI.

#modelscorewhereRAMreleased
247KAT-Coder-Pro V1 Kuaishou (Kwaipilot)62±3api price unknown2025-10
248A.X K1 (519B-A33B) SK Telecom62±1local~1091GB2025-12
249watt-tool-8B Watt AI62±7local~6.1GB2024-12
250FuseChat-Gemma-2-9B-Instruct FuseAI62±2local~7.6GB2024-11
251gpt-oss-120b OpenAI62±1api $0.26/M +local~67GB2025-08
more from Watt AI
157watt-tool-70B Watt AI67±7local~22GB2024-12

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▄▄▃▂▁ #180 of 334 * · 80% of its score · 1 test

Beats o1 (2024-12-17), o3-mini, DeepSeek R1 0528 here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Jamba 1.5 Large here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL v367.8% ✎▁▁▁▁▁▃▅█▅▄▁▁ beats 102/114medium · avg 52%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 80%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 watt-tool-8B · needs ~4.4 GB · from huggingface.co/eaddario
    chat in the terminal
    llama cli -hf eaddario/Watt-Tool-8B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf eaddario/Watt-Tool-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 watt-tool-8B · needs ~4.4 GB · from huggingface.co/eaddario

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/eaddario/Watt-Tool-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 watt-tool-8B · needs ~4.4 GB · from huggingface.co/eaddario
    chat in the terminal
    ollama run hf.co/eaddario/Watt-Tool-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 watt-tool-8B · needs ~4.5 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/watt-tool-8B
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/watt-tool-8B

Other ways to run it

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

Official weights and documentation: huggingface.co/watt-ai ↗

$ how the score was worked out · Berkeley Function Calling Lea… 80%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 80%Apache-2.0
prior · pull toward the middle▇▇▇▇▇▇ 20%
weighted average= 62.0

$ 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