whatmodel.sh / OpenHands LM 32B v0.1

OpenHands LM 32B v0.1

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

OpenHands LM 32B v0.1 is an open-weights language model from All Hands AI, released March 2025. Its published size is 32.76B parameters. Licence: mit.

Catalogue identity notes

Maker repo OpenHands/openhands-lm-32b-v0.1 @2487b7e (requested as all-hands/openhands-lm-32b-v0.1, which the HF API redirects to OpenHands/openhands-lm-32b-v0.1): licence tag mit. 32,763,876,352 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2025-03: month the maker's Hugging Face repo was created (createdAt 2025-03-26).

51.0±3.1#415 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 OpenHands LM 32B v0.1, out of 1132 with a score.

#modelscorewhereRAMreleased
541DeepSeek-TNG R1T2 Chimera TNG Technology Consulting51±10local~229GB2025-07
542Llama 3.1 Nemotron 51B Instruct NVIDIA51±2local~34GB2024-09
543OpenHands LM 32B v0.1 All Hands AI51±3local~21GB2025-03
544Bielik Minitron 7B v3.0 Instruct SpeakLeash51±4local~5.9GB2026-01
545Ministral 3 3B Reasoning 2512 Mistral51±1local~3.5GB2025-12

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #261 of 469 * · 96% of its score · 1 test

Beats Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B), GLM-4.7-Flash here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, QwQ-32B-Preview, Phi-3 Medium 128K Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Aider polyglot (225 exercises, two attempts)10.2% ✎▂·▃▃▅▂▃█▆▄▂▂ beats 3/49very hard · avg 8.5%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%sharp

$ 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 OpenHands LM 32B v0.1 · needs ~19.9 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/openhands-lm-32b-v0.1-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/openhands-lm-32b-v0.1-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 OpenHands LM 32B v0.1 · needs ~19.9 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/openhands-lm-32b-v0.1-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 OpenHands LM 32B v0.1 · needs ~19.9 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    ollama run hf.co/lmstudio-community/openhands-lm-32b-v0.1-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 OpenHands LM 32B v0.1 · needs ~18.4 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/openhands-lm-32b-v0.1-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/openhands-lm-32b-v0.1-4bit

Other ways to run it

  1. Run it as published · needs ~65.53 GB · from huggingface.co/OpenHands
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='OpenHands/openhands-lm-32b-v0.1', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/OpenHands ↗

$ how the score was worked out · Aider polyglot benchmark runs 96%

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
Aider polyglot benchmark runs1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%Apache-2.0
prior · pull toward the middle▇ 4%
weighted average= 51.0

$ 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