whatmodel.sh / Nemotron 3.5 Bolt E4B 4GB

Nemotron 3.5 Bolt E4B 4GB

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

Nemotron 3.5 Bolt E4B 4GB is an open-weights language model from NVIDIA, released October 2026. Its published size is 8B parameters (4B active per token) and a 64k-token context window. Licence: open-mdw-1.1.

Catalogue identity notes

Released Q4_K_M 4GB edition; results use its Q4_K_M column, never the BF16 column.

Model information sources

Release date ↗

56.4±7.3#303 of 961 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

Score within the LMArena (text) comparison set only.

$ how it compares

The LLMs ranked either side of Nemotron 3.5 Bolt E4B 4GB, out of 1192 with a score, then more from NVIDIA.

#modelscorewhereRAMreleased
394Llama3-Instruct-8B-WPO-HB-v2 wzhouad (WPO)56±2local~35GB2024-07
395Gemma-2-9B-It-SPPO-Iter3 UCLA AGI (SPPO)56±1local~7GB2024-06
396Nemotron 3.5 Bolt E4B 4GB NVIDIA56±7local~5.7GB2026-10
397Qwen3 4B Thinking 2507 Alibaba56±1local~4.2GB2025-08
398GPT-4 Turbo (2024-04-09) OpenAI56±0api $15.00/M2024-04
more from NVIDIA
119Nemotron 3 Ultra 550B-A55B NVIDIA68±1api $1.35/M +local~89GB2026-06
135Nemotron 3.5 Bolt 74B A9B NVIDIA68±2local~157GB2026-10
143Nemotron 3.5 Super VL 120B A12B NVIDIA67±1local~254GB2026-10

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▅▄▄▃▃▂▁ #200 of 347 * · 76% of its score · 1 test

Beats o1 (2024-12-17), o3-mini, DeepSeek R1 0528 here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Mellum2 12B-A2.5B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL v3 lab67.3% ✎▁▁▁▁▁▃▅█▆▅▄▁ beats 134/171medium · avg 58%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 76%blunt · at its level · small run
other tests2 not in a task · 0.0% of its score
testresultvs the others in its rundifficultycountswhy
MultiChallenge lab55.6% ✎▁·▁·▁▃▆▅▃▃█▅ beats 19/30hard · avg 28%—not counted yet: no other model in the same run to compare it with
RULER 64k lab85.8% ✎▁▁·▂·▂▃▄█▂▁▁ beats 19/26easy · avg 82%—not counted yet: no other model in the same run to compare it with

$ where to run it

llama.cpp · recommended

  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 Bolt E4B 4GB · needs ~4 GB · from huggingface.co/nvidia (official)
    chat in the terminal
    llama cli -hf nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB:Q4_K_M

LM Studio

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

    download it (macOS / Windows / Linux) ↗

  2. Run Nemotron 3.5 Bolt E4B 4GB · needs ~4 GB · from huggingface.co/nvidia (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Nemotron 3.5 Bolt E4B 4GB · needs ~4 GB · from huggingface.co/nvidia (official)
    chat in the terminal
    ollama run hf.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB:Q4_K_M

Official weights and documentation: huggingface.co/nvidia ↗

$ how the score was worked out · NVIDIA vendor-reported benchm… 76%

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 vendor-reported benchmark scores for its own Nemotron models (Hugging Face model cards) · lab-reported1Factual vendor-reported score (not licensed content)
prior · pull toward the middle
weighted average= 56.4

not counted (2)

NVIDIA vendor-reported benchmark scores for its own Nemotron models (Hugging Face model cards)MultiChallenge [correct]55.6%fewer than three models have this test yet, or this source ran it for this model alone
NVIDIA vendor-reported benchmark scores for its own Nemotron models (Hugging Face model cards)RULER 64k [correct]85.8%fewer than three models have this test yet, or this source ran it for this model alone

$ 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