LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Atlas Flash 7B Preview by open-atlas

 »  All LLMs  »  open-atlas  »  Atlas Flash 7B Preview   URL Share it on

  60   

Atlas Flash 7B Preview is an open-source language model by open-atlas. Features: 7b LLM, VRAM: 15.2GB, Context: 128K, License: mit, Quantized, LLM Explorer Score: 0.18.

  Arxiv:2312.14852   Arxiv:2501.12948   4bit   Ar   Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Bn   Ceb   Chat   Conversational   Cs   Dataset:baai/taco   Dataset:codeparrot/apps Dataset:rubenroy/gammacorpus-v...   De   En   Endpoints compatible   Es   Fa   Fr   Gemini-2.0   Gpt4   He   Hi   Id   It   Ja   Km   Ko   Lo   Ms   My   Nl   Pl   Pt   Quantized   Qwen2   R1   Region:us   Ru   Safetensors   Sharded   Tensorflow   Th   Tl   Tr   Trl   Ur   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/Spestly/Atlas-Flash-7B-Preview 

Atlas Flash 7B Preview Benchmarks

LLME Score: 0.1771
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Atlas Flash 7B Preview (Spestly/Atlas-Flash-7B-Preview)
🌟 Advertise your project 🚀

Atlas Flash 7B Preview Parameters and Internals

LLM NameAtlas Flash 7B Preview
Repository 🤗https://huggingface.co/Spestly/Atlas-Flash-7B-Preview 
Base Model(s)  DeepSeek R1 Distill Qwen 7B   deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Model Size7b
Required VRAM15.2 GB
Updated2025-09-22
Maintaineropen-atlas
Model Typeqwen2
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.3 GB: 3-of-4   1.1 GB: 4-of-4
Supported Languagesen zh fr es pt de it ru ja ko vi th ar fa he tr cs pl hi bn ur id ms lo my km tl nl
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.47.1
Tokenizer ClassLlamaTokenizer
Padding Token<|vision_pad|>
Vocabulary Size152064
Torch Data Typefloat16

Best Alternatives to Atlas Flash 7B Preview

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M 4bit986K / 4.3 GB42210
...B Instruct 1M Unsloth Bnb 4bit986K / 7.5 GB773
Qwen2.5 7B Instruct 1M 8bit986K / 8.1 GB774
Qwen2.5 7B Instruct 1M 6bit986K / 6.2 GB302
Mini Pathfinder128K / 15.2 GB160
A1 V002128K / 15.2 GB50
A1 V0.0.1128K / 15.2 GB50
CogitoDistil128K / 15.2 GB140
...still Qwen 7B Unsloth Bnb 4bit128K / 8.5 GB1035224
Alisia 7B Instruct V1128K / 15.4 GB1142
Note: green Score (e.g. "73.2") means that the model is better than Spestly/Atlas-Flash-7B-Preview.

Rank the Atlas Flash 7B Preview 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? 53232 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