whatmodel.sh / Tulu 2 70B

Tulu 2 70B

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

Tulu 2 70B is an open-weights language model from Allen Institute for AI, released November 2023. Its published size is 70B parameters. Licence: AI2 ImpACT Low-risk; Llama 2 base terms.

Catalogue identity notes

Exact full-precision model evaluated in the Tulu 2 paper (arXiv:2311.10702v2). QLoRA ablations are separate and not imported.

Model information sources

Release date ↗ · Weights licence ↗

45.6±1.8#432 of 719 LLMsfrom 5 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Tulu 2 70B, out of 828 with a score, then more from Allen Institute for AI.

#modelscorewhereRAMreleased
514GPT-3.5 Turbo (0613) OpenAI46±1comparison only2023-06
515Granite 3.3 8B Instruct IBM46±1local~6.3GB2025-04
516Tulu 2 70B Allen Institute for AI46±2local~28GB2023-11
517LFM2 8B-A1B Liquid AI46±1comparison only2025-10
518OpenChat 3.5 0106 Gemma OpenChat46±3local~6.9GB2024-03
more from Allen Institute for AI
493OLMo 2 13B Instruct (1124) Allen Institute for AI46±1local~9.6GB2024-12
557Code Tulu 2 34B Allen Institute for AI44±2local~72GB2023-11
599OLMo 2 7B Instruct (1124) Allen Institute for AI42±1local~5.8GB2024-12

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #383 of 458 * · 16% of its score · 1 test

Beats DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B, DeepSeek R1 Distill Llama 8B here, though they rank higher overall. Trails Qwen2.5 1.5B Instruct, WizardLM 13B V1.2, Falcon3 3B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Tulu 2: CodexEval pass@10 lab68.5% ✎▃▃▃·▆▃▃█▃▂▂▅ beats 14/25very easy · avg 86%▇▇▇▇▇▇ 16%sharp
math▁▂▃▅▆▅▄█▄▁▁▁ #227 of 398 * · 14% of its score · 1 test

Beats GPT-4o (2024-08-06), Command A (03-2025), GPT-4o (2024-11-20) here, though they rank higher overall. Trails Olmo 3 7B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K lab73.0% ✎▆▂▅█▅▅▃▆···▂ beats 22/25easy · avg 73%▇▇▇▇▇▇ 14%sharp · at its level
other tests3 not in a task · 68% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard lab68.4% ✎▁·····▂█▂▅·▁ beats 23/25easy · avg 77%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 46%sharp · at its level
MMLU lab67.3% ✎▁▁▃▃▄█▄▁█··▁ beats 22/25easy · avg 74%▇▇▇▇▇▇▇ 17%at its level
Tulu 2: TyDiQA gold passage, 1-shot F1 lab53.6% ✎▂··▁▃▂▂▂█▅▁▂ beats 18/25medium · avg 61%▇▇ 5.0%blunt · 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 Tulu 2 70B · needs ~41.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/tulu-2-70b-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/tulu-2-70b-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 Tulu 2 70B · needs ~41.4 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/tulu-2-70b-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 Tulu 2 70B · needs ~41.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/tulu-2-70b-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~137.95 GB · from huggingface.co/allenai
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='allenai/tulu-2-70b', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/allenai ↗

$ how the score was worked out · Tulu 2 — base and instruction… 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
Tulu 2 — base and instruction-tuned evaluations · lab-reported5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 45.6

$ 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