whatmodel.sh / Hammer2.1-0.5b

Hammer2.1-0.5b

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

Hammer2.1-0.5b is an open-weights language model from MadeAgents, released December 2024. Its published size is 0.49B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Maker repo MadeAgents/Hammer2.1-0.5b @a8e95a3: licence tag cc-by-nc-4.0. 493,789,952 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-12: month the maker's Hugging Face repo was created (createdAt 2024-12-12).

42.8±4.2#648 of 949 LLMsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Hammer2.1-0.5b, out of 1132 with a score, then more from MadeAgents.

#modelscorewhereRAMreleased
804MiniCPM-V 2.6 OpenBMB43±2local~6.4GB2024-08
805Qwen2.5 Coder 1.5B Instruct Alibaba43±1local~2.4GB2024-09
806Hammer2.1-0.5b MadeAgents43±4local~1.9GB2024-12
807LFM2 2.6B Liquid AI43±2local~3GB2025-09
808SmolLM3 3B Hugging Face43±1local~3.3GB2025-07
more from MadeAgents
497Hammer2.1-7b MadeAgents53±4local~5.9GB2024-12
540Hammer2.1-3b MadeAgents51±4local~3.3GB2024-12
601Hammer2.1-1.5b MadeAgents49±4local~2.4GB2024-12

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▄▄▃▂▁ #302 of 334 * · 92% of its score · 2 tests

Beats Magistral Small 1.0 (2506), Bielik 11B v2.3 Instruct, Mixtral 8x22B Instruct v0.1 here, though they rank higher overall. Trails Granite 4.0 H 350M, Qwen3 0.6B, Qwen2.5 1.5B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL V4 (December 2025 archive)21.2% ✎▁▁▁▃██▅▅▆▂▂▂ beats 6/77hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 57%typical
BFCL v345.4% ✎▁▁▁▁▁▃▅█▅▄▁▁ beats 23/114medium · avg 52%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 35%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 Hammer2.1-0.5b · needs ~0.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/Hammer2.1-0.5b-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/Hammer2.1-0.5b-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 Hammer2.1-0.5b · needs ~0.4 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/Hammer2.1-0.5b-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 Hammer2.1-0.5b · needs ~0.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/Hammer2.1-0.5b-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~0.99 GB · from huggingface.co/MadeAgents (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='MadeAgents/Hammer2.1-0.5b', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/MadeAgents ↗

$ how the score was worked out · Berkeley Function Calling Lea… 92%

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 archive2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 92%Apache-2.0
prior · pull toward the middle▇▇ 8%
weighted average= 42.8

$ 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