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

Aquif 3.5 8B Think by aquif-ai

 »  All LLMs  »  aquif-ai  »  Aquif 3.5 8B Think   URL Share it on

  19   
  Aquif   Aquif-3.5   Autotrain compatible   Coding   Conversational   De   En   Es   Fr   Hi   It   Ja   Language   Math   Pt   Qwen3   Region:us   Safetensors   Sharded   Small   Tensorflow   Th   Zh
Model Card on HF 🤗: https://huggingface.co/aquif-ai/aquif-3.5-8B-Think 

Aquif 3.5 8B Think Benchmarks

LLME Score: 0.28388
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Aquif 3.5 8B Think (aquif-ai/aquif-3.5-8B-Think)
🌟 Advertise your project 🚀

Aquif 3.5 8B Think Parameters and Internals

LLM NameAquif 3.5 8B Think
Repository 🤗https://huggingface.co/aquif-ai/aquif-3.5-8B-Think 
Model Size8b
Required VRAM16.4 GB
Updated2025-09-10
Maintaineraquif-ai
Model Typeqwen3
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.6 GB: 4-of-4
Supported Languagesen de it pt fr hi es th zh ja
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151669
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Aquif 3.5 8B Think

Best Alternatives
Context / RAM
Downloads
Likes
...n3 8B 320K Context 10X Massive320K / 16.4 GB540
Qwen3 8B 256K Context 8X Grand256K / 16.4 GB970
...wen3 8B 192K Context 6X Larger192K / 16.4 GB510
DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB270742955
DeepSeek R1 0528 Qwen3 8B128K / 16.4 GB1287316
...1 0528 Qwen3 8B Abliterated V1128K / 16.4 GB113927
...1 Qwen3 8B ArliAI RpR V4 Small128K / 16.4 GB118217
DeepSeek R1 0528 Qwen3 8B Bf16128K / 16.3 GB11682
...8 Qwen3 8B Abliterated V1 Bf16128K / 16.3 GB11601
OPC R1 8B128K / 16.4 GB1513
Note: green Score (e.g. "73.2") means that the model is better than aquif-ai/aquif-3.5-8B-Think.

Rank the Aquif 3.5 8B Think 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? 51262 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.
Release v20241124
  Support LLM Explorer