whatmodel.sh / Nemotron 3.5 Lightning 30B-A3B

Nemotron 3.5 Lightning 30B-A3B

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

Nemotron 3.5 Lightning 30B-A3B is an open-weights language model from NVIDIA, released August 2026. Its published size is 31.6B parameters (3.6B active per token) and a 262k-token context window. Licence: openmdw-1.1.

62.2±2.2#174 of 719 LLMsfrom 3 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Nemotron 3.5 Lightning 30B-A3B, out of 828 with a score, then more from NVIDIA.

#modelscorewhereRAMreleased
202Gemma 4 12B Google62±1local~8.5GB2026-06
203GPT-4.1 OpenAI62±1api $3.50/M2025-04
204Nemotron 3.5 Lightning 30B-A3B NVIDIA62±2api $0.087/M +local~20GB2026-08
205GLM-4.6V Z.ai62±2api $0.45/M +local~51GB2025-12
206Devstral 2 (2512) Mistral62±2local~75GB2025-12
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▁▁▁▃▆██▇▆▄▃▁ #126 of 458 * · 37% of its score · 1 test

Beats Qwen3.5 Plus, Gemini 2.5 Pro, Gemini 3.1 Flash-Lite here, though they rank higher overall. Trails Llama 3.1 Nemotron Ultra 253B v1 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Luau Leetcode fully solved (Torpedo Software)52.9% ✎▁▁▁▁·▁▂▃▅▃█▇ beats 11/49hard · avg 18%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 37%at its level
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #158 of 393 * · 42% of its score · 1 test

Beats MiniMax-M2, MiniCPM5 2B, Granite 4.2 30B here, though they rank higher overall. Trails LFM2.5 1.2B Thinking, LFM2.5 8B-A1B, LFM2.5 2.6B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1349.5 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 194/379avg 1268▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 42%blunt
other tests1 not in a task · 19% of its score
testresultvs the others in its rundifficultycountswhy
RobloxQA v2.0 multiple choice (Torpedo Software)87.7% ✎▁▁▃▃█▄▃▃▆▂▂▂ beats 7/49easy · avg 78%▇▇▇▇▇▇▇▇ 19%typical

$ where to run it

Through an API

api · Fireworks AI · $0.088/M · $0.05 in / $0.2 out per 1M tokens · 262k context · fireworks.ai ↗ · price sourceStandard base token rate from models.dev. Provider-specific tiers, long-context surcharges, caching and promotions may differ.

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 Nemotron 3.5 Lightning 30B-A3B · needs ~25.5 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-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 Nemotron 3.5 Lightning 30B-A3B · needs ~25.5 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-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 Nemotron 3.5 Lightning 30B-A3B · needs ~19.46 GB · from ollama.com
    chat in the terminal
    ollama run nemotron-3.5-lightning:30b

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 Nemotron 3.5 Lightning 30B-A3B · needs ~17.8 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bit

Official weights and documentation: huggingface.co/nvidia ↗

$ how the score was worked out · Roblox LLM Leaderboard (Torpe… 56%, LMArena leaderboard dataset 42%

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
Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 56%MIT
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇ 42%CC BY 4.0
prior · pull toward the middle▇ 2%
weighted average= 62.2

$ 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