whatmodel.sh / H2O-Danube2 1.8B Chat

H2O-Danube2 1.8B Chat

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

H2O-Danube2 1.8B Chat is an open-weights language model from H2O.ai, released April 2024. Its published size is 1.83B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo h2oai/h2o-danube2-1.8b-chat @6d8114c: licence tag apache-2.0. 1,831,201,280 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-04: month the maker's Hugging Face repo was created (createdAt 2024-04-05).

30.1±3.5#858 of 949 LLMsfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of H2O-Danube2 1.8B Chat, out of 1132 with a score.

#modelscorewhereRAMreleased
1027SmolLM2 1.7B Instruct Hugging Face30±1local~2.6GB2024-10
1028Yi 6B Chat 01.AI30±2local~5.1GB2023-11
1029H2O-Danube2 1.8B Chat H2O.ai30±4local~2.7GB2024-04
1030Llama 3.2 1B Instruct Meta30±1api $0.020/M +local~2.2GB2024-09
1031Falcon 7B (base) TII30±1local~5.9GB2023-04

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests2 not in a task · 94% of its score
testresultvs the others in its rundifficultycountswhy
CPTUB average (SpeakLeash, 0-5 judge scale)32.8% ✎▃▂▂▂▃█▃▆▅▄▂▃ beats 2/95easy · avg 66%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 77%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)47.7% ✎▃▁▁▁▁▁▁▃▂█▅▁ beats 63/276medium · avg 73%▇▇▇▇▇▇▇ 18%noisy

$ 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 H2O-Danube2 1.8B Chat · needs ~1.1 GB · from huggingface.co/h2oai (official)
    chat in the terminal
    llama cli -hf h2oai/h2o-danube2-1.8b-chat-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf h2oai/h2o-danube2-1.8b-chat-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 H2O-Danube2 1.8B Chat · needs ~1.1 GB · from huggingface.co/h2oai (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/h2oai/h2o-danube2-1.8b-chat-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 H2O-Danube2 1.8B Chat · needs ~1.1 GB · from huggingface.co/h2oai (official)
    chat in the terminal
    ollama run hf.co/h2oai/h2o-danube2-1.8b-chat-GGUF:Q4_K_M

MLX (Mac)

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run H2O-Danube2 1.8B Chat · needs ~1.1 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/h2o-danube2-1.8b-chat-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/h2o-danube2-1.8b-chat-4bit

Other ways to run it

  1. Run it as published · needs ~3.66 GB · from huggingface.co/h2oai (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='h2oai/h2o-danube2-1.8b-chat', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/h2oai ↗

$ how the score was worked out · SpeakLeash CPTUB (Complex Pol… 77%, Open Portuguese LLM Leaderboa… 18%

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
SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 77%MIT
Open Portuguese LLM Leaderboard (archived)1▇▇▇▇▇ 18%Apache-2.0
prior · pull toward the middle▇▇ 6%
weighted average= 30.1

$ 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