whatmodel.sh / Falcon 7B (base)

Falcon 7B (base)

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

Falcon 7B (base) is an open-weights language model from TII, released April 2023. Its published size is 7.22B parameters and a 2k-token context window. Licence: apache-2.0.

Catalogue identity notes

Pretrained Falcon-7B (not falcon-7b-instruct).

29.8±0.6#643 of 719 LLMsfrom 34 benchmark results across 7 sources

$ how it compares

The LLMs ranked either side of Falcon 7B (base), out of 828 with a score, then more from TII.

#modelscorewhereRAMreleased
738SmolLM2 1.7B Instruct Hugging Face30±1local~2.6GB2024-10
739Llama 3.2 1B Instruct Meta30±1api $0.020/M +local~2.2GB2024-09
740Falcon 7B (base) TII30±1local~5.9GB2023-04
741Llama 2 7B Chat Meta30±1local~5.8GB2023-07
742Baichuan2-7B-Base Baichuan30±1local~17GB2023-08
more from TII
233Falcon-H1R 7B TII60±1local~6GB2026-01
332Falcon-H1 34B Instruct TII54±3local~23GB2025-05
494Falcon-H1 7B Instruct TII46±3local~6GB2025-05

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests18 not in a task · 100% of its score
testresultvs the others in its rundifficultycountswhy
ARC Challenge +243.7% ✎▁·▁··▁▁▇▂█▆▃ beats 19/26easy · avg 85%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%sharp · several runs
WinoGrande +267.2% ✎▁····▁··▁▂█▄ beats 17/26easy · avg 89%▇▇▇▇▇ 13%at its level · several runs
BoolQ +273.5% ✎▂▃▂▅▆▂▅▆█▂▂▂ beats 18/26easy · avg 91%▇▇▇▇ 10%at its level · several runs
HellaSwag +276.3% ✎▃···▁▇▅█▇▃▁▁ beats 22/26very easy · avg 92%▇▇▇ 7.2%at its level · several runs
ARC Easy +270.8% ✎▁▁·▁▁▄▅▄█▅▁▃ beats 20/26easy · avg 88%▇▇▇ 7.1%at its level · several runs
OpenBookQA +230.6% ✎█·▁▁▃·▁▃▅▇▃▄ beats 17/26easy · avg 84%▇▇▇ 6.7%at its level · several runs
Natural Questions (closed book)22.1% ✎▁·▁·▁▂▁▂·▅▃█ beats 17/28medium · avg 58%▇▇ 4.3%typical
PIQA +279.5% ✎▁·▁··▁▁▃█▅█▃ beats 25/26easy · avg 88%▇▇ 4.3%blunt · at its level · several runs
10 more tests
testresultvs the others in its rundifficultycountswhy
SciQ +194.0% ✎▁·▁·▁·▃▅▃█▄▁ beats 21/26very easy · avg 98%▇▇ 4.2%several runs
Social IQA +142.1% ✎▁···▁▃█▁▁▁·▁ beats 13/26medium · avg 63%▇ 2.5%blunt · several runs
Factual knowledge recall, Premium2k exact match (zero-shot)23.6% ✎▅····▃▅·██·█ beats 7/13medium · avg 59%▇ 2.1%typical
Factual knowledge recall, Premium2k exact match (10-shot)30.4% ✎▃▅▃··▅▃·█▃▃▅ beats 5/13easy · avg 67%▇ 1.8%at its level
LAMBADA (OpenAI version), last-word accuracy74.6% ✎▁··▂▁▁▁▂▆█▅▃ beats 24/26very easy · avg 89%▇ 1.2%blunt · at its level
TriviaQA58.7% ✎▁··▁█▃▃▁▄▅▄█ beats 22/28easy · avg 79%▇ 0.6%at its level · noisy
Open PT-LLM Leaderboard average (9 Portuguese tasks)36.9% ✎▃▁▁▁▃▁▁▁▂█▅▁ beats 46/276medium · avg 73%▇ 0.6%noisy
TruthfulQA MC234.3% ✎▅▃█▆▁▂▅···▁▁ beats 2/31medium · avg 64%▇ 0.3%blunt · at its level
HaluEval QA hallucination detection (accuracy)46.7% ✎█▁▁·▁▁·▁▁▁▁▁ beats 2/27medium · avg 70%▇ 0.2%sharp · too hard for it · noisy
COPA53.8% ✎▅·▃·▃··█▃··▃ beats 1/8easy · avg 92%▇ 0.2%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 Falcon 7B (base) · needs ~5 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/falcon-7b-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/falcon-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 Falcon 7B (base) · needs ~5 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/falcon-7b-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 Falcon 7B (base) · needs ~4.2 GB · from ollama.com
    chat in the terminal
    ollama run falcon:7b-text

Other ways to run it

  1. Run it as published · needs ~14.43 GB · from huggingface.co/tiiuae (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='tiiuae/falcon-7b', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/tiiuae ↗

$ how the score was worked out · Stability AI — original Stabl… 48%, OLMo: Accelerating the Scienc… 23%, Textbooks Are All You Need II… 19% and 4 more

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
Stability AI — original StableLM zero-shot evaluation outputs10▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 48%Apache-2.0
OLMo: Accelerating the Science of Language Models — authors' own runs8▇▇▇▇▇▇▇ 23%CC BY 4.0
Textbooks Are All You Need II: phi-1.5 technical report — authors' own runs8▇▇▇▇▇▇ 19%CC BY 4.0
Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)4▇▇ 5%Apache-2.0
Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall (arXiv:2404.16164v1)2▇ 4%CC-BY-4.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items (arXiv:2410.14897v1)1▇ 0%CC-BY-4.0
prior · pull toward the middle▇ 0%
weighted average= 29.8

$ 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