Ether0 by futurehouse

 ยป  All LLMs  ยป  futurehouse  ยป  Ether0   URL Share it on

  Arxiv:2506.17238 Base model:finetune:mistralai/... Base model:mistralai/mistral-s...   Chemistry   Conversational Dataset:futurehouse/ether0-ben...   En   Instruct   Mistral   Reasoning   Region:us   Safetensors   Sharded   Smiles   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/futurehouse/ether0 

Ether0 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ether0 (futurehouse/ether0)
๐ŸŒŸ Advertise your project ๐Ÿš€

Ether0 Parameters and Internals

LLM NameEther0
Repository ๐Ÿค—https://huggingface.co/futurehouse/ether0 
Base Model(s)  ...istral Small 24B Instruct 2501   mistralai/Mistral-Small-24B-Instruct-2501
Model Size24b
Required VRAM95.3 GB
Updated2025-09-23
Maintainerfuturehouse
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-21   4.6 GB: 2-of-21   4.5 GB: 3-of-21   4.5 GB: 4-of-21   4.5 GB: 5-of-21   4.5 GB: 6-of-21   4.5 GB: 7-of-21   4.5 GB: 8-of-21   4.5 GB: 9-of-21   4.5 GB: 10-of-21   4.5 GB: 11-of-21   4.5 GB: 12-of-21   4.5 GB: 13-of-21   4.5 GB: 14-of-21   4.5 GB: 15-of-21   4.5 GB: 16-of-21   4.5 GB: 17-of-21   4.5 GB: 18-of-21   4.5 GB: 19-of-21   4.5 GB: 20-of-21   4.7 GB: 21-of-21
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.49.0
Tokenizer ClassLlamaTokenizerFast
Vocabulary Size131136
Torch Data Typefloat32

Best Alternatives to Ether0

Best Alternatives
Context / RAM
Downloads
Likes
...ral Nemo Instruct 24B Merge V11000K / 24.6 GB90
Cydonia 24B V4.1128K / 47.3 GB50064
M3.2 24B Loki V1.3128K / 47.3 GB100133
Cydonia 24B V4128K / 47.3 GB85734
Skyfall 31B V4128K / 62.9 GB24018
Codex 24B Small 3.2128K / 47.3 GB54454
...2 PaintedFantasy Visage V3 34B128K / 68.4 GB16822
MS3.2 PaintedFantasy V2 24B128K / 47.3 GB21730
Cydonia R1 24B V4128K / 47.3 GB16929
MS3.2 24B Magnum Diamond128K / 47.3 GB39440
Note: green Score (e.g. "73.2") means that the model is better than futurehouse/ether0.

Rank the Ether0 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 51557 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124