whatmodel.sh / AceReason-Nemotron-1.0-14B

AceReason-Nemotron-1.0-14B

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

AceReason-Nemotron-1.0-14B is an open-weights language model from NVIDIA, released May 2025. Its published size is 14.77B parameters. Licence: nvidia-open-model-license.

Catalogue identity notes

NVIDIA's own model, repo nvidia/AceReason-Nemotron-14B @b244ed5 (licence nvidia-open-model-license). Math and code RL model 'starting from the DeepSeek-R1-Distilled-Qwen-14B' (version 1.0; the report prints 'AceReason-Nemotron-1.0-14B'). Printed as 'AceReason-Nemotron-1.0-14B' 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/AceReason-Nemotron-14B @b244ed5: 14,770,033,664 parameters (dense).

50.7±1.8#330 of 719 LLMsfrom 3 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of AceReason-Nemotron-1.0-14B, out of 828 with a score, then more from NVIDIA.

#modelscorewhereRAMreleased
397Llama-3-Instruct-8B-SimPO-ExPO Chujie Zheng (ExPO)51±1local~6.6GB2024-05
398LFM2 24B-A2B Liquid AI51±1local~16GB2026-02
399AceReason-Nemotron-1.0-14B NVIDIA51±2local~10GB2025-05
400Llama-3-Instruct-8B-SimPO Princeton NLP51±1local~6.6GB2024-05
401Athene-70B Nexusflow51±1local~29GB2024-07
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▁▁▁▃▆██▇▆▄▃▁ #283 of 458 · 99% of its score · 3 tests

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, WizardLM 70B V1.0, Yi 1.5 9B Chat here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LiveCodeBench Pro 2025Q2 (Easy) lab47.9% ✎▄·▄····▄▄▄█▄ beats 1/7medium · avg 45%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 43%at its level
LiveCodeBench Pro 2025Q2 (Medium) lab2.2% ✎▃▃····▃·█·▃▃ beats 1/7very hard · avg 2.4%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 35%sharp · too hard for it
LiveCodeBench v6 (Aug 2024–May 2025) lab58.7% ✎▄▄···▄·▄▄█·▄ beats 1/7medium · avg 57%▇▇▇▇▇▇▇▇ 20%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 AceReason-Nemotron-1.0-14B · needs ~8.99 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/nvidia_AceReason-Nemotron-14B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/nvidia_AceReason-Nemotron-14B-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 AceReason-Nemotron-1.0-14B · needs ~8.99 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/nvidia_AceReason-Nemotron-14B-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 AceReason-Nemotron-1.0-14B · needs ~8.99 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/nvidia_AceReason-Nemotron-14B-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 AceReason-Nemotron-1.0-14B · needs ~8.3 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/AceReason-Nemotron-14B-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/AceReason-Nemotron-14B-4bit

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= 50.7

$ 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