whatmodel.sh / Cogito v1 Preview Llama 3B

Cogito v1 Preview Llama 3B

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

Cogito v1 Preview Llama 3B is an open-weights language model from Deep Cogito, released March 2025. Its published size is 3.61B parameters and a 128k-token context window. Licence: llama3.2.

Catalogue identity notes

Maker repo deepcogito/cogito-v1-preview-llama-3B @5a0ad6f: licence tag llama3.2. 3,606,752,256 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2025-03: month the maker's Hugging Face repo was created (createdAt 2025-03-31). Ollama tags cogito:3b-v1-preview-llama-q4_K_M, cogito:3b-v1-preview-llama-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.

46.2±4.4#416 of 719 LLMsfrom 3 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Cogito v1 Preview Llama 3B, out of 828 with a score, then more from Deep Cogito.

#modelscorewhereRAMreleased
494Falcon-H1 7B Instruct TII46±3local~6GB2025-05
495GPT-3.5 Turbo (1106) OpenAI46±1comparison only2023-11
496Cogito v1 Preview Llama 3B Deep Cogito46±4local~3.4GB2025-03
497Code Llama 70B Instruct Meta46±1local~28GB2024-01
498Hermes 2 Pro Llama 3 8B Nous Research46±3local~6.6GB2024-04
more from Deep Cogito
388Cogito v1 Preview Llama 8B Deep Cogito51±5local~6.2GB2025-03

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests3 not in a task · 91% of its score
testresultvs the others in its rundifficultycountswhy
Open PT-LLM Leaderboard average (9 Portuguese tasks)66.8% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 130/276medium · avg 73%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 38%at its level · noisy
EuroEval HellaSwag (English), test split, 5-shot generative MC, accuracy64.9% ✎▃·▁▁▂▁▂▅█▇▄▁ beats 41/100medium · avg 68%▇▇▇▇▇▇▇▇▇▇▇▇ 31%at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy73.3% ✎▁▁▁▁▁▁▁▂▄█▄▃ beats 45/146easy · avg 83%▇▇▇▇▇▇▇▇▇ 23%at its level · 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 Cogito v1 Preview Llama 3B · needs ~2.2 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/cogito-v1-preview-llama-3B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/cogito-v1-preview-llama-3B-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 Cogito v1 Preview Llama 3B · needs ~2.2 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/cogito-v1-preview-llama-3B-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 Cogito v1 Preview Llama 3B · needs ~2.67 GB · from ollama.com
    chat in the terminal
    ollama run cogito:3b-v1-preview-llama-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 Cogito v1 Preview Llama 3B · needs ~1.8 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/deepcogito-cogito-v1-preview-llama-3B-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/deepcogito-cogito-v1-preview-llama-3B-4bit

Official weights and documentation: huggingface.co/deepcogito ↗

$ how the score was worked out · EuroEval leaderboards (result… 53%, Open Portuguese LLM Leaderboa… 38%

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
EuroEval leaderboards (results collection), English generative leaderboard2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 53%MIT
Open Portuguese LLM Leaderboard (archived)1▇▇▇▇▇▇▇▇▇▇▇ 38%Apache-2.0
prior · pull toward the middle▇▇▇ 9%
weighted average= 46.2

$ 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