whatmodel.sh / Falcon3 1B Instruct

Falcon3 1B Instruct

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

Falcon3 1B Instruct is an open-weights language model from TII, released December 2024. Its published size is 1.67B parameters and a 8k-token context window. Licence: falcon-llm.

Catalogue identity notes

Maker repo tiiuae/Falcon3-1B-Instruct @28ba225: licence tag other (falcon-llm-license). 1,669,408,768 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2024-12: month the maker's Hugging Face repo was created (createdAt 2024-12-14). Ollama tags falcon3:1b-instruct-q4_K_M, falcon3:1b-instruct-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.

23.9±4.2#678 of 719 LLMsfrom 7 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of Falcon3 1B Instruct, out of 828 with a score, then more from TII.

#modelscorewhereRAMreleased
782OPT-6.7B Meta24±1local~16GB2022-05
783RWKV-4-Raven 14B RWKV (BlinkDL)24±2comparison only2023-04
784Falcon3 1B Instruct TII24±4local~2.4GB2024-12
785StableLM-Base-Alpha 3B v2 Stability AI24±1local~13GB2023-08
786Qwen1.5 1.8B Chat Alibaba24±2local~2.7GB2024-01
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

agent tasks▃▁▃▆█▆▅▅▅▄▃▁ #299 of 300 * · 51% of its score · 2 tests

Beats Gemma 3 1B here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
BFCL v319.7% ✎▃▁▁▁▁▃▅█▅▄▁▁ beats 1/114medium · avg 52%▇▇▇▇▇▇▇▇▇▇▇ 27%blunt · at its level
BFCL V4 (December 2025 archive)11.1% ✎▁▃▁▂██▅▅▆▂▂▂ beats 2/77hard · avg 32%▇▇▇▇▇▇▇▇▇▇ 25%typical
coding▁▁▁▃▆██▇▆▄▃▁ #436 of 458 · 23% of its score · 4 tests

Beats Qwen3.5 2B, Molmo 7B-D (0924), DeepSeek R1 Distill Qwen 1.5B here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
CodeReviewQA: automated code refinement, exact match rate3.4% ✎▁▃▁▁▁▁▂▂▃█▅▄ beats 1/47hard · avg 33%▇▇▇▇▇ 12%typical
CodeReviewQA: solution identification (hard), invariant accuracy0.0% ✎▃··▁▂▂▃▂█▃▄▂ beats 1/47medium · avg 54%▇▇▇ 6.8%sharp · too hard for it · noisy
CodeReviewQA: change localisation (hard), invariant accuracy0.0% ✎█▂▁▁▂▂▂▃▅▅▅▇ beats 2/47medium · avg 36%▇ 3.6%sharp · too hard for it · noisy
CodeReviewQA: change type recognition, invariant accuracy55.8% ✎▁▁▁······▃▃█ beats 7/47easy · avg 67%▇ 0.8%blunt · at its level · noisy
other tests1 not in a task · 18% of its score
testresultvs the others in its rundifficultycountswhy
Open PT-LLM Leaderboard average (9 Portuguese tasks)44.2% ✎▃▁▁▁▁▁▃▁▂█▅▁ beats 55/276medium · avg 73%▇▇▇▇▇▇▇ 18%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 Falcon3 1B Instruct · needs ~1.1 GB · from huggingface.co/tiiuae (official)
    chat in the terminal
    llama cli -hf tiiuae/Falcon3-1B-Instruct-GGUF:q4_k_m
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf tiiuae/Falcon3-1B-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 Falcon3 1B Instruct · needs ~1.1 GB · from huggingface.co/tiiuae (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/tiiuae/Falcon3-1B-Instruct-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 Falcon3 1B Instruct · needs ~1.5 GB · from ollama.com
    chat in the terminal
    ollama run falcon3:1b-instruct-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 Falcon3 1B Instruct · needs ~0.9 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Falcon3-1B-Instruct-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Falcon3-1B-Instruct-4bit

Official weights and documentation: huggingface.co/tiiuae ↗

$ how the score was worked out · Berkeley Function Calling Lea… 51%, CodeReviewQA: The Code Review… 23%, Open Portuguese LLM Leaderboa… 18%

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
Berkeley Function Calling Leaderboard result archive2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 51%Apache-2.0
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)4▇▇▇▇▇▇▇ 23%CC-BY-4.0
Open Portuguese LLM Leaderboard (archived)1▇▇▇▇▇ 18%Apache-2.0
prior · pull toward the middle▇▇ 8%
weighted average= 23.9

$ 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