whatmodel.sh / OpenReasoning-Nemotron-32B

OpenReasoning-Nemotron-32B

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

OpenReasoning-Nemotron-32B is an open-weights language model from NVIDIA, released July 2025. Its published size is 32.76B parameters. Licence: cc-by-4.0.

Catalogue identity notes

NVIDIA's own model, repo nvidia/OpenReasoning-Nemotron-32B @2e8aa1b (licence cc-by-4.0). Reasoning model 'derivative of Qwen2.5-32B', post-trained for math, code and science. Printed as 'OpenReasoning-Nemotron-32B' in the Nemotron-Cascade report (arXiv 2512.13607v2) Table 9; listed so the report's NVIDIA rows join the existing LiveCodeBench Pro 25Q2 runs.

Model information sources

Release date ↗ · Weights licence ↗

safetensors metadata of nvidia/OpenReasoning-Nemotron-32B @2e8aa1b: 32,763,876,352 parameters (dense).

59.4±1.5#203 of 719 LLMsfrom 3 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of OpenReasoning-Nemotron-32B, out of 828 with a score, then more from NVIDIA.

#modelscorewhereRAMreleased
243Gemini 2.0 Flash-Lite Preview (02-05) Google60±3comparison only2025-02
244QwQ-32B Alibaba59±1local~21GB2025-03
245OpenReasoning-Nemotron-32B NVIDIA59±2local~21GB2025-07
246DeepSeek V3 (Dec '24) DeepSeek59±1api $0.46/M +local~337GB2024-12
247Gemma 2 9B IT SimPO Princeton NLP59±1local~7.6GB2024-07
more from NVIDIA
98Nemotron 3 Ultra 550B-A55B NVIDIA69±1api $1.35/M +local~89GB2026-06
155Nemotron Cascade 2 30B-A3B NVIDIA66±1local~20GB2026-03
168Nemotron 3 Super 120B-A12B NVIDIA65±1api $0.28/M +local~73GB2026-03

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #177 of 458 · 99% of its score · 3 tests

Beats Qwen3.5 9B, Devstral 2 (2512), Gemini 2.5 Flash here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 8B Reasoning 2512, Phi-4-reasoning 14B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LiveCodeBench Pro 2025Q2 (Medium) lab8.3% ✎▃▃····▃·█·▃▃ beats 6/7very hard · avg 2.4%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 61%sharp · too hard for it
LiveCodeBench Pro 2025Q2 (Easy) lab66.2% ✎▄·▄····▄▄▄█▄ beats 6/7medium · avg 45%▇▇▇▇▇▇▇▇▇▇ 26%at its level
LiveCodeBench v6 (Aug 2024–May 2025) lab70.2% ✎▄▄···▄·▄▄█·▄ beats 4/7medium · avg 57%▇▇▇▇▇ 12%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 OpenReasoning-Nemotron-32B · needs ~19.85 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/nvidia_OpenReasoning-Nemotron-32B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/nvidia_OpenReasoning-Nemotron-32B-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 OpenReasoning-Nemotron-32B · needs ~19.85 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/nvidia_OpenReasoning-Nemotron-32B-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 OpenReasoning-Nemotron-32B · needs ~19.85 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/nvidia_OpenReasoning-Nemotron-32B-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 OpenReasoning-Nemotron-32B · needs ~18.4 GB, Mac only · from huggingface.co/litmudoc
    chat in the terminal
    mlx_lm.chat --model litmudoc/OpenReasoning-Nemotron-32B-MLX-Q4
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model litmudoc/OpenReasoning-Nemotron-32B-MLX-Q4

Official weights and documentation: huggingface.co/nvidia ↗

$ how the score was worked out · NVIDIA — Nemotron-Cascade: Sc… 99%

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
NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models · lab-reported3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 59.4

$ 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