ALIA 40B Fc 2605 by BSC-LT

 »  All LLMs  »  BSC-LT  »  ALIA 40B Fc 2605   URL Share it on

ALIA 40B Fc 2605 is an open-source language model by BSC-LT. Features: 40b LLM, VRAM: 80.4GB, Context: 160K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.27.

  Arxiv:2502.08489   Base model:bsc-lt/alia-40b Base model:finetune:bsc-lt/ali...   Conversational   Dataset:agent-ark/toucan-1.5m Dataset:allenai/dolci-instruct... Dataset:glaiveai/glaive-functi...   Dataset:nanbeige/toolmind   Dataset:nvidia/when2call Dataset:salesforce/xlam-functi...   Dataset:team-ace/toolace   Endpoints compatible   Instruct   Llama   Region:eu   Safetensors   Sharded   Tensorflow

ALIA 40B Fc 2605 Benchmarks

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

ALIA 40B Fc 2605 Parameters and Internals

LLM NameALIA 40B Fc 2605
Repository 🤗https://huggingface.co/BSC-LT/ALIA-40b-fc-2605 
Base Model(s)  ALIA 40B   BSC-LT/ALIA-40b
Model Size40b
Required VRAM80.4 GB
Updated2026-06-02
MaintainerBSC-LT
Model Typellama
Instruction-BasedYes
Model Files  4.9 GB: 1-of-17   4.9 GB: 2-of-17   4.9 GB: 3-of-17   4.8 GB: 4-of-17   4.9 GB: 5-of-17   4.9 GB: 6-of-17   4.9 GB: 7-of-17   4.8 GB: 8-of-17   4.9 GB: 9-of-17   4.9 GB: 10-of-17   4.9 GB: 11-of-17   4.8 GB: 12-of-17   4.9 GB: 13-of-17   4.9 GB: 14-of-17   4.9 GB: 15-of-17   3.0 GB: 16-of-17   4.2 GB: 17-of-17
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length163840
Model Max Length163840
Transformers Version4.57.1
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size256000

Best Alternatives to ALIA 40B Fc 2605

Best Alternatives
Context / RAM
Downloads
Likes
ALIA 40B Instruct 2601160K / 80.4 GB39899
Note: green Score (e.g. "73.2") means that the model is better than BSC-LT/ALIA-40b-fc-2605.

Rank the ALIA 40B Fc 2605 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? 54215 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