whatmodel.sh / Llama 3.1 Nemotron 70B Instruct

Llama 3.1 Nemotron 70B Instruct

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

Llama 3.1 Nemotron 70B Instruct is an open-weights language model from NVIDIA, released October 2024. Its published size is 70.6B parameters and a 128k-token context window. Licence: llama3.1.

Catalogue identity notes

Arena entry 'llama-3.1-nemotron-70b-instruct' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'llama-3.1-nemotron-70b-instruct' as 'Llama-3.1-Nemotron-70B-Instruct' (Nvidia, Llama 3.1), linking https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct. Maker repo nvidia/Llama-3.1-Nemotron-70B-Instruct-HF @031d404: licence tag llama3.1. 70,553,706,496 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-10: month the maker's Hugging Face repo was created (createdAt 2024-10-12). The ollama 'nemotron' library is described as 'Llama-3.1-Nemotron-70B-Instruct'.

51.8±0.9#315 of 719 LLMsfrom 19 benchmark results across 10 sources

$ how it compares

The LLMs ranked either side of Llama 3.1 Nemotron 70B Instruct, out of 828 with a score, then more from NVIDIA.

#modelscorewhereRAMreleased
379Bielik 11B v2.2 Instruct SpeakLeash52±3local~8.5GB2024-08
380Granite 4.0 H Small (32B-A9B) IBM52±1api $0.11/M +local~21GB2025-09
381Llama 3.1 Nemotron 70B Instruct NVIDIA52±1local~43GB2024-10
382Palmyra X4 (palmyra-x-004) Writer52±4comparison only2024-10
383Nemotron-4 340B Instruct NVIDIA52±2comparison only2024-06
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▁▁▁▃▆██▇▆▄▃▁ #266 of 458 * · 17% of its score · 2 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, Mistral NeMo Instruct (2407), QwQ-32B-Preview here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Aider code editing (133 Exercism Python exercises, two attempts)54.9% ✎▁·▁▂▄▁▆▄█▆▂▂ beats 21/62medium · avg 54%▇▇▇▇▇▇ 14%at its level
WebApp1K-React pass@1 (onekq-ai)22.4% ✎▃▁▃█▁▄▅▃▄▇▁▄ beats 3/31medium · avg 44%▇ 3.6%sharp · at its level · noisy
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #213 of 393 · 40% of its score · 6 tests

Beats Granite 4.2 8B, Mistral Small 4 (119B-A6.5B), Gemma 2 9B IT SimPO here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, Granite 4.0 H Micro 3B, Gemma 3n E4B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena-Hard (v0.1, GPT-4-1106 judge)84.9% ✎▂▁▁▅█▅▄▃▃▅▃▁ beats 56/60medium · avg 52%▇▇▇▇▇▇▇▇ 20%sharp · at its level
LMArena (text)1298.7 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 127/379avg 1268▇▇▇ 7.3%blunt
Arena-Hard v2.0 hard prompts (style control, Gemini-2.5 judge)10.3% ✎▂·▃▅▅·▃█▆▂▂▂ beats 2/22very hard · avg 12%▇▇▇ 6.3%sharp
AlpacaEval 2 length-controlled66.1% ✎▁▁▃▄▆██▆▃▃▁▁ beats 146/155medium · avg 47%▇ 3.6%at its level · small run
IFEval prompt-level loose79.9% ✎▁▂▁▂▁▃▁▃█▂▂▁ beats 11/25easy · avg 79%▇ 1.9%small run
Arena-Hard v2.0 creative writing (GPT-4.1 + Gemini-2.5 judges)26.9% ✎▆▂▂▆▂▂▃█▂▃·▂ beats 8/22hard · avg 19%▇ 1.5%sharp · noisy
math▁▂▃▅▆▅▄█▄▁▁▁ #287 of 398 * · 9.0% of its score · 2 tests

Trails DeepSeek R1 Distill Qwen 1.5B, Phi-2 (2.7B), StarCoder2 15B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MATH (subset unspecified)55.0% ✎▂▄▄▃█▇▅▆▄▃▄▁ beats 31/80medium · avg 58%▇▇ 4.5%at its level · small run
GSM8K84.7% ✎▂▂▂▅▅▆▅▇█▇▄▃ beats 102/146very easy · avg 87%▇▇ 4.4%sharp · small run
other tests9 not in a task · 33% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard78.5% ✎▁▁▁▁▂▄▅▅█▃▄▁ beats 107/129easy · avg 77%▇▇▇ 6.8%sharp · at its level · small run
DROP68.8% ✎▅··▅·█▅█▅▃▃▅ beats 8/17easy · avg 65%▇▇ 5.7%at its level · small run
MMLU83.8% ✎▁▁▁▁▁▂▃▅█▃▆▃ beats 151/183easy · avg 79%▇▇ 4.8%small run
LiveBench 2024-08-3143.1% ✎▄█·▄·▄▄·▄··▄ beats 0/7medium · avg 42%▇▇ 4.5%at its level
EvalPerf correctness (118 tasks, 20240328)61.8% ✎▂·▂▃▂▆▅▆▆▆▃█ beats 2/29easy · avg 76%▇▇ 4.2%typical
BRIDGE clinical text, zero-shot average (87 tasks)32.8% ✎▁▁▁▁▁▂▂▃▄▆█▃ beats 38/97hard · avg 32%▇▇ 3.8%blunt · at its level
PopQA36.4% ✎▁▁▂▃▅▃▂█▂▃·▄ beats 29/36hard · avg 35%▇ 1.6%blunt · at its level · small run
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy93.5% ✎▁▁▁▁▁▁▁▂▄█▄▃ beats 131/146easy · avg 83%▇ 0.8%noisy
1 more test
testresultvs the others in its rundifficultycountswhy
TruthfulQA MC262.6% ✎█▅▇▅▁▄▁▇▅▄▁▁ beats 47/73medium · avg 64%▇ 0.6%blunt · at its level · small run

$ 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 3.1 Nemotron 70B Instruct · needs ~42.5 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/Llama-3.1-Nemotron-70B-Instruct-HF-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 Llama 3.1 Nemotron 70B Instruct · needs ~42.5 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/Llama-3.1-Nemotron-70B-Instruct-HF-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 Llama 3.1 Nemotron 70B Instruct · needs ~42.86 GB · from ollama.com
    chat in the terminal
    ollama run nemotron:70b-instruct-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 Llama 3.1 Nemotron 70B Instruct · needs ~39.7 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/nvidia_Llama-3.1-Nemotron-70B-Instruct-HF_4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/nvidia_Llama-3.1-Nemotron-70B-Instruct-HF_4bit

Official weights and documentation: huggingface.co/nvidia ↗

$ how the score was worked out · Tülu 3: Pushing Frontiers in… 34%, Arena-Hard-Auto v0.1 leaderbo… 20%, Aider code editing benchmark… 14% and 7 more

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
Tülu 3: Pushing Frontiers in Open Language Model Post-Training (Lambert et al., Ai2)9▇▇▇▇▇▇▇▇▇▇ 34%CC BY 4.0
Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)1▇▇▇▇▇▇ 20%Apache-2.0
Aider code editing benchmark runs (old edit leaderboard)1▇▇▇▇ 14%Apache-2.0
Arena-Hard-Auto v2.0-Preview leaderboard (repository README)2▇▇ 8%Apache-2.0
LMArena leaderboard dataset1▇▇ 7%CC BY 4.0
LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets1▇ 5%Apache-2.0 (stated in the LiveBench datasheet)
EvalPlus / EvalPerf published evaluation runs1▇ 4%Apache-2.0
BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)1▇ 4%MIT
WebApp1K models leaderboard (onekq-ai)1▇ 4%MIT
EuroEval leaderboards (results collection), English generative leaderboard1▇ 1%MIT
prior · pull toward the middle▇ 0%
weighted average= 51.8

$ 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