whatmodel.sh / Dolphin 2.2.1 Mistral 7B

Dolphin 2.2.1 Mistral 7B

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

Dolphin 2.2.1 Mistral 7B is an open-weights language model from Cognitive Computations, released October 2023. Its published size is 7.24B parameters. Licence: apache-2.0.

Catalogue identity notes

Arena entry 'dolphin-2.2.1-mistral-7b' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'dolphin-2.2.1-mistral-7b' as 'Dolphin-2.2.1-Mistral-7B' (Cognitive Computations, Apache-2.0), linking https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b. Maker repo dphn/dolphin-2.2.1-mistral-7b @20f78ab: licence tag apache-2.0. 7,241,748,480 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-10: month the maker's Hugging Face repo was created (createdAt 2023-10-30). Repo now served as dphn/dolphin-2.2.1-mistral-7b (renamed from ehartford/).

36.7±1.7#580 of 719 LLMsfrom 3 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of Dolphin 2.2.1 Mistral 7B, out of 828 with a score, then more from Cognitive Computations.

#modelscorewhereRAMreleased
671Gemma 1.1 7B IT Google37±1local~7.1GB2024-04
672Code Llama 7B Python Meta37±1local~5.8GB2023-08
673Dolphin 2.2.1 Mistral 7B Cognitive Computations37±2local~6.1GB2023-10
674Code Llama 13B (base) Meta37±1local~9.2GB2023-08
675Qwen1.5 7B Chat Alibaba37±1local~6.5GB2024-02
more from Cognitive Computations
554Dolphin 2.6 Mixtral 8x7B Cognitive Computations44±1local~29GB2023-12

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #351 of 393 · 99% of its score · 3 tests

Beats Gemma 4 E2B, Code Llama 70B Instruct, Phi-3-mini-4k-instruct (June 2024 update) here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Granite 4.0 H 350M here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled13.1% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 31/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%typical
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1060.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 30/95avg 1201▇▇▇▇▇▇▇▇▇▇ 25%blunt
LMArena (text)1152.2 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 41/379avg 1268▇▇▇▇▇▇▇▇▇▇ 24%blunt

$ 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 Dolphin 2.2.1 Mistral 7B · needs ~4.4 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/dolphin-2.2.1-mistral-7B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/dolphin-2.2.1-mistral-7B-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 Dolphin 2.2.1 Mistral 7B · needs ~4.4 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/dolphin-2.2.1-mistral-7B-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 Dolphin 2.2.1 Mistral 7B · needs ~4.84 GB · from ollama.com
    chat in the terminal
    ollama run dolphin-mistral:7b-v2.2.1-q4_K_M

Official weights and documentation: huggingface.co/dphn ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 50%, Polyrating: A Cost-Effective… 25%, LMArena leaderboard dataset 24%

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
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇▇▇▇▇▇ 25%CC-BY-4.0
LMArena leaderboard dataset1▇▇▇▇▇▇▇ 24%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 36.7

$ 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