whatmodel.sh / Falcon 7B Instruct

Falcon 7B Instruct

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

Falcon 7B Instruct is an open-weights language model from TII, released April 2023. Its published size is 7.22B parameters. Licence: apache-2.0.

Catalogue identity notes

tiiuae/falcon-7b-instruct @8782b5c (created 2023-04-25, licence apache-2.0). TII's 2023 instruct fine-tune of Falcon-7B (catalogued base falcon-7b). Independent rows: AlpacaEval 1.0 and 2.0 and Vectara HHEM (2025 set).

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 7,217,189,760 parameters.

25.4±2.0#670 of 719 LLMsfrom 7 benchmark results across 3 sources

$ how it compares

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

#modelscorewhereRAMreleased
773GPT-3 curie (API base model) OpenAI26±1comparison only2020-06
774Alpaca 13B Stanford CRFM26±2comparison only2023-03
775Falcon 7B Instruct TII25±2local~5.9GB2023-04
776Qwen2 0.5B Instruct Alibaba25±2local~1.8GB2024-06
777Pythia 12B EleutherAI25±1local~9.5GB2023-02
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

chat & writing▁▁▃▃▅▄▅█▆▆▇▃ #386 of 393 * · 49% of its score · 2 tests

Beats Phi-2 (2.7B) here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled4.0% ✎▁▃▂▃▆▆█▆▄▄▁▁ beats 3/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇ 26%too hard for it
AlpacaEval 1.0 win rate (vs text-davinci-003, GPT-4 judge)45.7% ✎▂▂·▆·▇▃▆█▆▄▂ beats 6/45very easy · avg 96%▇▇▇▇▇▇▇▇▇ 23%sharp · at its level · noisy
other tests5 not in a task · 49% of its score
testresultvs the others in its rundifficultycountswhy
Natural Questions (closed book)13.6% ✎▁·▁·▁▂▁▂·▅▂█ beats 11/28medium · avg 58%▇▇▇▇▇▇▇▇▇▇▇▇▇ 33%typical
TriviaQA39.2% ✎▁··▁█▃▃▁▄▅▄█ beats 14/28easy · avg 79%▇▇ 5.7%at its level · noisy
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)70.1% ✎▃▁▂▃▄▄█▆▃▂▂▁ beats 0/140very easy · avg 94%▇▇ 5.7%blunt · noisy
TruthfulQA MC244.1% ✎▅▃█▆▁▂▅···▁▁ beats 17/31medium · avg 64%▇ 3.0%blunt · at its level
HaluEval QA hallucination detection (accuracy)29.7% ✎█▁▁·▁▁·▁▁▁▁▁ beats 1/27medium · avg 70%▇ 1.6%sharp · too hard for it · 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 Instruct · needs ~4.8 GB · from huggingface.co/QuantFactory
    chat in the terminal
    llama cli -hf QuantFactory/falcon-7b-instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf QuantFactory/falcon-7b-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 Falcon 7B Instruct · needs ~4.8 GB · from huggingface.co/QuantFactory

    open in LM Studio ↗

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

Official weights and documentation: huggingface.co/tiiuae ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 49%, Hallucinations Leaderboard re… 44%, Vectara hallucination leaderb… 6%

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)2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 49%Apache-2.0
Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)4▇▇▇▇▇▇▇▇▇▇▇▇▇ 44%Apache-2.0
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)1▇▇ 6%Apache-2.0
prior · pull toward the middle▇ 2%
weighted average= 25.4

$ 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