Name: Falcon 180B
Author: tiiuae

Falcon 180B is an open-source language model by tiiuae. Features: 180b LLM, VRAM: 193.8GB, License: proprietary, HF Score: 65.5, LLM Explorer Score: 0.16, Arc: 69.2, HellaSwag: 88.9, MMLU: 69.6, TruthfulQA: 45.2, WinoGrande: 86.7, GSM8K: 33.2, HumanEval: 35.4.

Arxiv:1911.02150 Arxiv:2005.14165 Arxiv:2101.00027 Arxiv:2104.09864 Arxiv:2205.14135 Arxiv:2306.01116 Autotrain compatible Dataset:tiiuae/falcon-refinedw... De En Es Falcon Fr Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/tiiuae/falcon-180B

Falcon 180B Benchmarks

ARC: 69.2 vs 96.7 (so35)^-28.4%

HellaSwag: 88.89 vs 95.3 (gpt4)^-6.7%

MMLU: 69.59 vs 88.3 (so35)^-21.2%

TruthfulQA: 45.16 vs 59 (gpt4)^-23.5%

WinoGrande: 86.74 vs 87.5 (gpt4)^-0.9%

GSM8K: 33.21 vs 96.4 (so35)^-65.5%

HumanEvalA: 24.08

Python Eva: 35.37 vs 92 (so35)^-61.6%

Java Eval: 28.48

Javascript: 31.68

CPP Eval: 28.57

Julia Eval: 24.53

D Eval: 14.1

Lua Eval: 26.71

Racket Eva: 10.56

Rust Eval: 25

Swift Eval: 15.82

LLME Score: 0.1638

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

🌟 Advertise your project 🚀

Falcon 180B Parameters and Internals

LLM Name	Falcon 180B
Repository 🤗	https://huggingface.co/tiiuae/falcon-180B
Model Size	180b
Required VRAM	193.8 GB
Updated	2025-11-04
Maintainer	tiiuae
Model Type	falcon
Model Files	4.6 GB: 1-of-81 4.4 GB: 2-of-81 4.4 GB: 3-of-81 4.4 GB: 4-of-81 4.4 GB: 5-of-81 4.4 GB: 6-of-81 4.4 GB: 7-of-81 4.4 GB: 8-of-81 4.4 GB: 9-of-81 4.4 GB: 10-of-81 4.4 GB: 11-of-81 4.4 GB: 12-of-81 4.4 GB: 13-of-81 4.4 GB: 14-of-81 4.4 GB: 15-of-81 4.4 GB: 16-of-81 4.4 GB: 17-of-81 4.4 GB: 18-of-81 4.4 GB: 19-of-81 4.4 GB: 20-of-81 4.4 GB: 21-of-81 4.4 GB: 22-of-81 4.4 GB: 23-of-81 4.4 GB: 24-of-81 4.4 GB: 25-of-81 4.4 GB: 26-of-81 4.4 GB: 27-of-81 4.4 GB: 28-of-81 4.4 GB: 29-of-81 4.4 GB: 30-of-81 4.4 GB: 31-of-81 4.4 GB: 32-of-81 4.4 GB: 33-of-81 4.4 GB: 34-of-81 4.4 GB: 35-of-81 4.4 GB: 36-of-81 4.4 GB: 37-of-81 4.4 GB: 38-of-81 4.4 GB: 39-of-81 4.4 GB: 40-of-81 4.4 GB: 41-of-81 4.4 GB: 42-of-81 4.4 GB: 43-of-81 4.4 GB: 44-of-81
Supported Languages	en de es fr
Gated Model	Yes
Model Architecture	FalconForCausalLM
License	proprietary
Transformers Version	4.32.0
Is Biased	0
Vocabulary Size	65024
Torch Data Type	bfloat16

Quantized Models of the Falcon 180B

Model	Likes	Downloads	VRAM
Falcon 180B GGUF	20	10	0 GB
Falcon 180B GPTQ	10	15	94 GB

Best Alternatives to Falcon 180B

Best Alternatives	Context / RAM	Downloads	Likes
Largefalcon	2K / 411.4 GB	104	0
...buddy Falcon 180B V12 Preview0	2K / 358.1 GB	815	0
...buddy Falcon 180B V13 Preview0	2K / 358.1 GB	788	2
Airoboros 180B 2.2.1	2K / 154.2 GB	754	17
...buddy Falcon 180B V13 Preview2	2K / 358.1 GB	9	1
...buddy Falcon 180B V13 Preview2	2K / 358.1 GB	5	1
...buddy Falcon 180B V13 Preview1	2K / 358.1 GB	5	4
...buddy Falcon 180B V12 Preview0	2K / 358.1 GB	11	0
...alcon 180B Omniquant W3a16g512	2K / 69.4 GB	8	3
... 180B Wizard Alpaca Dolly Orca	0K / 358 GB	1883	4

Rank the Falcon 180B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 52392 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Falcon 180B by tiiuae

» All LLMs » tiiuae » Falcon 180B URL Share it on