whatmodel.sh / OLMo 2 13B Instruct (1124)

OLMo 2 13B Instruct (1124)

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

OLMo 2 13B Instruct (1124) is an open-weights language model from Allen Institute for AI, released December 2024. Its published size is 13.72B parameters and a 4k-token context window. Licence: apache-2.0.

Catalogue identity notes

Maker repo allenai/OLMo-2-1124-13B-Instruct @3a5c85b: licence tag apache-2.0. 13,716,198,400 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2024-12: month the maker's Hugging Face repo was created (createdAt 2024-12-18). Ollama tags olmo2:13b-1124-instruct-q4_K_M, olmo2:13b-1124-instruct-q8_0 are the library's instruct/chat builds of this checkpoint (tag names on the pinned tags page); download sizes are estimated from the parameter count.

46.3±1.4#414 of 719 LLMsfrom 11 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of OLMo 2 13B Instruct (1124), out of 828 with a score, then more from Allen Institute for AI.

#modelscorewhereRAMreleased
491Jamba 1.5 Mini AI21 Labs46±1local~34GB2024-08
492MedGemma 4B IT Google46±3local~4.1GB2025-05
493OLMo 2 13B Instruct (1124) Allen Institute for AI46±1local~9.6GB2024-12
494Falcon-H1 7B Instruct TII46±3local~6GB2025-05
495GPT-3.5 Turbo (1106) OpenAI46±1comparison only2023-11
more from Allen Institute for AI
516Tulu 2 70B Allen Institute for AI46±2local~28GB2023-11
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

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #246 of 393 * · 15% of its score · 2 tests

Beats Mistral Small 4 (119B-A6.5B), Ministral 3 14B Reasoning 2512, Qwen2.5 Coder 32B Instruct here, though they rank higher overall. Trails Flan-T5 XXL, Granite 4.0 H 1B, Granite 4.0 1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled lab39.5% ✎▃▃·▁▁█▇▅·▁·▁ beats 15/22medium · avg 42%▇▇▇▇ 11%at its level
IFEval prompt-level loose lab82.6% ✎▁▃▁▃▁▄▁▁█▃▃▁ beats 15/22easy · avg 80%▇▇ 3.8%typical
math▁▂▃▅▆▅▄█▄▁▁▁ #321 of 398 * · 19% of its score · 2 tests

Beats Athene-70B, Gemma 2 9B IT, GPT-3.5 Turbo (0125) here, though they rank higher overall. Trails Gemma 7B (base), DeepSeek R1 Distill Qwen 1.5B, Tulu 2 DPO 13B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GSM8K lab87.4% ✎▂▃··▃▂▅█▆▃▂▃ beats 14/22very easy · avg 88%▇▇▇▇▇ 12%sharp
MATH (subset unspecified) lab39.2% ✎▃▃█▂▂▆·····▁ beats 6/22medium · avg 61%▇▇▇ 6.9%at its level
other tests7 not in a task · 65% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard lab63.0% ✎▁▄·▁▁·▅█·▄▄▁ beats 6/22easy · avg 75%▇▇▇▇▇▇▇▇▇▇ 26%sharp · at its level
MMLU lab68.5% ✎▁▂·▁·▁▁█·▃▃▅ beats 7/22easy · avg 77%▇▇▇▇▇▇▇▇▇▇ 25%at its level
PopQA lab28.8% ✎▁▁▁▃▃▃▁█▁▃·▄ beats 12/21hard · avg 32%▇▇ 4.4%blunt · at its level
TruthfulQA MC2 lab64.3% ✎▃▃▂·▃▃·▅█▂▅▂ beats 13/21medium · avg 63%▇ 3.7%blunt · at its level
EuroEval HellaSwag (English), test split, 5-shot generative MC, accuracy68.5% ✎▃·▁▁▂▁▂▅█▇▄▁ beats 45/100medium · avg 68%▇ 3.2%at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy83.0% ✎▁▁▁▁▁▁▁▂▄█▄▃ beats 84/146easy · avg 83%▇ 2.3%at its level · noisy
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)89.2% ✎▁▁▂▃▄▄█▆▃▂▂▁ beats 22/140very easy · avg 94%▇ 1.3%blunt · maxed out · noisy

$ 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 OLMo 2 13B Instruct (1124) · needs ~8.4 GB · from huggingface.co/allenai
    chat in the terminal
    llama cli -hf allenai/OLMo-2-1124-13B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf allenai/OLMo-2-1124-13B-Instruct-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 OLMo 2 13B Instruct (1124) · needs ~8.4 GB · from huggingface.co/allenai

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/allenai/OLMo-2-1124-13B-Instruct-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 OLMo 2 13B Instruct (1124) · needs ~8.73 GB · from ollama.com
    chat in the terminal
    ollama run olmo2:13b-1124-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 OLMo 2 13B Instruct (1124) · needs ~7.7 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/OLMo-2-1124-13B-Instruct-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/OLMo-2-1124-13B-Instruct-4bit

Weights and documentation: huggingface.co/allenai ↗

$ how the score was worked out · 2 OLMo 2 Furious (Team OLMo,… 92%, EuroEval leaderboards (result… 5%, Vectara hallucination leaderb… 1%

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
2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct models · lab-reported8▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 92%CC BY 4.0
EuroEval leaderboards (results collection), English generative leaderboard2▇▇ 5%MIT
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)1▇ 1%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 46.3

$ 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