whatmodel.sh / CoALM-8B

CoALM-8B

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

CoALM-8B is an open-weights language model from UIUC ConvAI & Oumi (CoALM), released February 2025. Its published size is 8.03B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Maker repo uiuc-convai/CoALM-8B @920d7aa: licence tag cc-by-nc-4.0. 8,030,261,248 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2025-02: month the maker's Hugging Face repo was created (createdAt 2025-02-03).

48.3±4.0#491 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 CoALM-8B, out of 1132 with a score, then more from UIUC ConvAI & Oumi (CoALM).

#modelscorewhereRAMreleased
625Qwen2.5 7B Instruct Alibaba48±1api $0.30/M +local~6GB2024-09
626DeepSeek R1 Distill Qwen 7B DeepSeek48±1local~6GB2025-01
627CoALM-8B UIUC ConvAI & Oumi (CoALM)48±4local~6.6GB2025-02
628XwinCoder-34B Xwin-LM48±1local~23GB2023-11
629StarChat2 15B v0.1 Hugging Face48±1local~12GB2024-03
more from UIUC ConvAI & Oumi (CoALM)
308CoALM-405B UIUC ConvAI & Oumi (CoALM)59±7local~854GB2025-02
606CoALM-70B UIUC ConvAI & Oumi (CoALM)49±4local~29GB2025-02

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▄▄▃▂▁ #264 of 334 * · 93% of its score · 2 tests

Beats o3-mini, DeepSeek R1 0528 Qwen3 8B, Llama 4 Maverick (402B-A17B) here, though they rank higher overall. Trails Granite 4.0 1B, SmolLM3 3B, Phi-3.5-mini-instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL V4 (December 2025 archive)26.8% ✎▁▁▁▂██▅▅▆▂▂▂ beats 17/77hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 60%at its level
BFCL v354.5% ✎▁▁▁▁▁▃▅█▅▄▁▁ beats 55/114medium · avg 52%▇▇▇▇▇▇▇▇▇▇▇▇▇ 32%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 CoALM-8B · needs ~4.9 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/CoALM-8B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/CoALM-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 CoALM-8B · needs ~4.9 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/CoALM-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 CoALM-8B · needs ~4.9 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/CoALM-8B-GGUF:Q4_K_M

Other ways to run it

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

Official weights and documentation: huggingface.co/uiuc-convai ↗

$ how the score was worked out · Berkeley Function Calling Lea… 93%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%Apache-2.0
prior · pull toward the middle▇▇ 7%
weighted average= 48.3

$ 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