whatmodel.sh / Llama 3.3 Nemotron Super 49B v1.5

Llama 3.3 Nemotron Super 49B v1.5

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

Llama 3.3 Nemotron Super 49B v1.5 is an open-weights language model from NVIDIA, released July 2025. Its published size is 49B parameters and a 131k-token context window. Licence: nvidia-open-model.

57.5±1.4#226 of 719 LLMsfrom 4 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Llama 3.3 Nemotron Super 49B v1.5, out of 828 with a score, then more from NVIDIA.

#modelscorewhereRAMreleased
268Qwen3 Coder 30B-A3B Instruct Alibaba58±1api $0.12/M +local~20GB2025-07
269Nova 2 Lite Amazon58±2api $0.94/M2025-10
270Llama 3.3 Nemotron Super 49B v1.5 NVIDIA58±1local~18GB2025-07
271Nemotron 3 Nano 30B-A3B NVIDIA58±1api $0.087/M +local~20GB2025-12
272Ministral 3 14B Reasoning 2512 Mistral58±1local~10GB2025-12
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▁▁▁▃▆██▇▆▄▃▁ #200 of 458 · 81% of its score · 3 tests

Beats Qwen3.5 4B, Qwen3-VL 32B Instruct, Falcon-H1R 7B here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 3B Reasoning 2512, DeepSeek-Coder-V2 Instruct (0724) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LiveCodeBench Pro 2025Q2 (Medium) lab6.1% ✎▃▃····▃·█·▃▃ beats 4/7very hard · avg 2.4%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 46%sharp · too hard for it
LiveCodeBench Pro 2025Q2 (Easy) lab61.9% ✎▄·▄····▄▄▄█▄ beats 3/7medium · avg 45%▇▇▇▇▇▇▇▇▇▇ 25%at its level
LiveCodeBench v6 (Aug 2024–May 2025) lab68.1% ✎▄▄···▄·▄▄█·▄ beats 3/7medium · avg 57%▇▇▇▇ 11%at its level
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #167 of 393 * · 18% of its score · 1 test

Beats MiniCPM5 2B, Granite 4.2 30B, Seed-OSS 36B Instruct here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, LFM2.5 1.2B Thinking, LFM2.5 8B-A1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1342.9 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 181/379avg 1268▇▇▇▇▇▇▇ 18%blunt

$ 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 Llama 3.3 Nemotron Super 49B v1.5 · needs ~29.9 GB · from huggingface.co/unsloth
    chat in the terminal
    llama cli -hf unsloth/Llama-3_3-Nemotron-Super-49B-v1_5-GGUF:UD-Q4_K_XL
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf unsloth/Llama-3_3-Nemotron-Super-49B-v1_5-GGUF:UD-Q4_K_XL

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Llama 3.3 Nemotron Super 49B v1.5 · needs ~29.9 GB · from huggingface.co/unsloth

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/unsloth/Llama-3_3-Nemotron-Super-49B-v1_5-GGUF@UD-Q4_K_XL -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 Llama 3.3 Nemotron Super 49B v1.5 · needs ~29.9 GB · from huggingface.co/unsloth
    chat in the terminal
    ollama run hf.co/unsloth/Llama-3_3-Nemotron-Super-49B-v1_5-GGUF:UD-Q4_K_XL

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 Llama 3.3 Nemotron Super 49B v1.5 · needs ~28.1 GB, Mac only · from huggingface.co/jesusoctavioas
    chat in the terminal
    mlx_lm.chat --model jesusoctavioas/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model jesusoctavioas/Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit

Official weights and documentation: huggingface.co/nvidia ↗

$ how the score was worked out · NVIDIA — Nemotron-Cascade: Sc… 81%, LMArena leaderboard dataset 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
NVIDIA — Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models · lab-reported3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%CC BY 4.0
LMArena leaderboard dataset1▇▇▇▇▇ 18%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 57.5

$ 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