whatmodel.sh / Falcon3 7B Instruct

Falcon3 7B Instruct

+ contribute

Falcon3 7B Instruct is an open-weights language model from TII, released November 2024. Its published size is 7.46B parameters and a 32k-token context window. Licence: falcon-llm.

Catalogue identity notes

Maker repo tiiuae/Falcon3-7B-Instruct @1e57a0e: licence tag other (falcon-llm-license). 7,455,550,464 parameters from the Hugging Face safetensors metadata. Dense, so active = total. Released 2024-11: month the maker's Hugging Face repo was created (createdAt 2024-11-29). Ollama tags falcon3:7b-instruct-q4_K_M, falcon3:7b-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.

44.0±2.7#462 of 719 LLMsfrom 7 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of Falcon3 7B Instruct, out of 828 with a score, then more from TII.

#	model	score	where	RAM	released
549	Granite 20B Code Instruct (8K) IBM	44±1	local	~14GB	2024-04
550	Qwen2 7B Instruct Alibaba	44±1	local	~6GB	2024-06
551	Falcon3 7B Instruct TII	44±3	local	~5.9GB	2024-11
552	Xwin-LM 70B v0.1 Xwin-LM	44±1	local	~28GB	2023-09
553	Qwen3-VL 2B Instruct Alibaba	44±1	local	~2.7GB	2025-10
	more from TII
233	Falcon-H1R 7B TII	60±1	local	~6GB	2026-01
332	Falcon-H1 34B Instruct TII	54±3	local	~23GB	2025-05
494	Falcon-H1 7B Instruct TII	46±3	local	~6GB	2025-05

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #274 of 300 * · 38% of its score · 2 tests

Beats Magistral Small 1.0 (2506), Bielik 11B v2.3 Instruct, Mixtral 8x22B Instruct v0.1 here, though they rank higher overall. Trails Granite 4.0 H 350M, Qwen3 0.6B, Qwen2.5 1.5B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
BFCL V4 (December 2025 archive)	24.0% ✎	▁▁▁▂██▅▅▆▂▂▂ beats 13/77	hard · avg 32%	▇▇▇▇▇▇▇▇▇▇ 24%	typical
BFCL v3	43.6% ✎	▁▁▁▁▁▃▅█▅▄▁▁ beats 21/114	medium · avg 52%	▇▇▇▇▇▇ 14%	blunt · at its level

coding▁▁▁▃▆██▇▆▄▃▁ #331 of 458 · 44% of its score · 4 tests

Beats GLM-4.7-Flash, Qwen3-VL 4B Instruct, LFM2.5 2.6B here, though they rank higher overall. Trails Phi-3-mini-128k-instruct (Apr 2024), DeepSeek LLM 67B Chat, WizardLM 70B V1.0 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
CodeReviewQA: solution identification (hard), invariant accuracy	35.3% ✎	▃··▁▂▂▃▃█▃▄▂ beats 19/47	medium · avg 54%	▇▇▇▇▇▇▇ 17%	sharp · at its level · noisy
CodeReviewQA: change localisation (hard), invariant accuracy	22.6% ✎	█▂▁▁▂▂▂▃▅▅▅▇ beats 21/47	medium · avg 36%	▇▇▇▇▇▇ 15%	sharp · noisy
CodeReviewQA: automated code refinement, exact match rate	14.3% ✎	▁▁▁▁▁▁▃▂▃█▅▄ beats 9/47	hard · avg 33%	▇▇▇▇▇ 12%	typical
CodeReviewQA: change type recognition, invariant accuracy	73.2% ✎	▁▁▁······▁▃█ beats 25/47	easy · avg 67%	▇ 0.3%	blunt · at its level · noisy

other tests1 not in a task · 15% of its score

test	result	vs the others in its run	difficulty	counts	why
Open PT-LLM Leaderboard average (9 Portuguese tasks)	72.8% ✎	▃▁▁▁▁▁▁▁▂█▅▁ beats 200/276	medium · avg 73%	▇▇▇▇▇▇ 15%	at its level · noisy

$ where to run it

llama.cpp · recommended

version

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 ↗
Run Falcon3 7B Instruct · needs ~4.6 GB · from huggingface.co/tiiuae (official)
chat in the terminal
llama cli -hf tiiuae/Falcon3-7B-Instruct-GGUF:q4_k_m
Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf tiiuae/Falcon3-7B-Instruct-GGUF:q4_k_m

LM Studio

version

Install LM Studio · Open the app once before using the lms command.
download it (macOS / Windows / Linux) ↗
Run Falcon3 7B Instruct · needs ~4.6 GB · from huggingface.co/tiiuae (official)
open in LM Studio ↗
Or download it in the terminal
lms get https://huggingface.co/tiiuae/Falcon3-7B-Instruct-GGUF@q4_k_m -y
Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

Install Ollama
download it (macOS / Windows) ↗
Linux
curl -fsSL https://ollama.com/install.sh | sh
Run Falcon3 7B Instruct · needs ~4.98 GB · from ollama.com
chat in the terminal
ollama run falcon3:7b-instruct-q4_K_M

MLX (Mac)

version

Install MLX (Mac) · Apple silicon Macs only, text only.
with uv
uv tool install mlx-lm
or
pip install mlx-lm
Run Falcon3 7B Instruct · needs ~4.2 GB, Mac only · from huggingface.co/mlx-community
chat in the terminal
mlx_lm.chat --model mlx-community/Falcon3-7B-Instruct-4bit
Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model mlx-community/Falcon3-7B-Instruct-4bit

Official weights and documentation: huggingface.co/tiiuae ↗

$ how the score was worked out · CodeReviewQA: The Code Review… 44%, Berkeley Function Calling Lea… 38%, Open Portuguese LLM Leaderboa… 15%

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

source	results	share of the score	licence
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)	4	▇▇▇▇▇▇▇▇▇▇▇▇▇ 44%	CC-BY-4.0
Berkeley Function Calling Leaderboard result archive	2	▇▇▇▇▇▇▇▇▇▇▇▇ 38%	Apache-2.0
Open Portuguese LLM Leaderboard (archived)	1	▇▇▇▇ 15%	Apache-2.0
prior · pull toward the middle		▇ 3%
weighted average		= 44.0

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit 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 2026-10-11 02:20 UTC · sources and licences · json