Tiiuae Falcon 7B Instruct Bnb 8bit Smashed by PrunaAI

 »  All LLMs  »  PrunaAI  »  Tiiuae Falcon 7B Instruct Bnb 8bit Smashed   URL Share it on

Tiiuae Falcon 7B Instruct Bnb 8bit Smashed is an open-source language model by PrunaAI. Features: 7b LLM, VRAM: 7.2GB, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

  8-bit   8bit   Bitsandbytes   Custom code   Falcon   Instruct   Pruna-ai   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Tiiuae Falcon 7B Instruct Bnb 8bit Smashed Benchmarks

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

Tiiuae Falcon 7B Instruct Bnb 8bit Smashed Parameters and Internals

Model Type 
text generation
Training Details 
Data Sources:
WikiText
Methodology:
Compression with llm-int8
Hardware Used:
NVIDIA A100-PCIE-40GB
Input Output 
Input Format:
pt
Accepted Modalities:
text
Output Format:
text
LLM NameTiiuae Falcon 7B Instruct Bnb 8bit Smashed
Repository 🤗https://huggingface.co/PrunaAI/tiiuae-falcon-7b-instruct-bnb-8bit-smashed 
Base Model(s)  ORIGINAL_REPO_NAME   /ORIGINAL_REPO_NAME
Model Size7b
Required VRAM7.2 GB
Updated2025-09-23
MaintainerPrunaAI
Model Typefalcon
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.2 GB: 2-of-2
Quantization Type8bit
Model ArchitectureFalconForCausalLM
Transformers Version4.48.2
Is Biased0
Vocabulary Size65024
Torch Data Typebfloat16

Best Alternatives to Tiiuae Falcon 7B Instruct Bnb 8bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
Falcon 7B Instruct Bnb 8bit2K / 7.2 GB51
Falcon 7B Instruct Bnb 4bit2K / 4 GB51
Claire 7B FR Instruct 0.12K / 13.9 GB586
... Openassistant Toxicity Reduce2K / 30.4 GB50
New Falcon2K / 4.3 GB81
Claire 7B 0.1 Instruct2K / 7.2 GB81
New Falcon2K / 4.3 GB00
Falcon 7B Instruct0K / 14.4 GB863911032
Falcon 7B Instruct Quant0K / 4 GB151
Falcon 7B Instruct Ft0K / 13.9 GB60
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/tiiuae-falcon-7b-instruct-bnb-8bit-smashed.

Rank the Tiiuae Falcon 7B Instruct Bnb 8bit Smashed 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? 53999 in total.

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