whatmodel.sh / Dracarys2-72B-Instruct

Dracarys2-72B-Instruct

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

Dracarys2-72B-Instruct is an open-weights language model from Abacus.AI, released September 2024. Its published size is 72.71B parameters. Licence: other (tongyi-qianwen).

Catalogue identity notes

Maker repo abacusai/Dracarys2-72B-Instruct @298cb07: licence tag other (tongyi-qianwen). 72,706,203,648 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-09: month the maker's Hugging Face repo was created (createdAt 2024-09-30).

55.0±2.5#317 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Dracarys2-72B-Instruct, out of 1132 with a score.

#modelscorewhereRAMreleased
417Krutrim-2 Instruct Krutrim (Ola)55±5local~9.4GB2025-02
418Spark-X2.5 1.7B iFLYTEK (SparkLLM)55±1local~2.7GB2026-08
419Dracarys2-72B-Instruct Abacus.AI55±3local~28GB2024-09
420GigaChat 3.5 Ultra Instruct (432B-A28B) Sber55±1local~457GB2026-07
421Llama 3.1 405B Instruct Meta55±1api $2.40/M +local~160GB2024-07

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #208 of 469 * · 97% of its score · 1 test

Beats Qwen3.5 4B, Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B) here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 3B Reasoning 2512, DeepSeek-Coder-V2 Instruct (0724) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Aider code editing (133 Exercism Python exercises, two attempts)66.9% ✎▁·▁▂▄▁▆▄█▆▂▂ beats 43/62medium · avg 54%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%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 Dracarys2-72B-Instruct · needs ~47.4 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/Dracarys2-72B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/Dracarys2-72B-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 Dracarys2-72B-Instruct · needs ~47.4 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/Dracarys2-72B-Instruct-GGUF@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 Dracarys2-72B-Instruct · needs ~25.5 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/Dracarys2-72B-Instruct-GGUF:IQ2_XXS

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 Dracarys2-72B-Instruct · needs ~40.9 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Dracarys2-72B-Instruct-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Dracarys2-72B-Instruct-4bit

Other ways to run it

  1. Run it as published · needs ~145.41 GB · from huggingface.co/abacusai (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='abacusai/Dracarys2-72B-Instruct', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/abacusai ↗

$ how the score was worked out · Aider code editing benchmark… 97%

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
Aider code editing benchmark runs (old edit leaderboard)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%Apache-2.0
prior · pull toward the middle▇ 3%
weighted average= 55.0

$ 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