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

AnFeng V3 Avocet by NLPark

 »  All LLMs  »  NLPark  »  AnFeng V3 Avocet   URL Share it on

  8338   

AnFeng V3 Avocet is an open-source language model by NLPark. Features: 35b LLM, VRAM: 69.5GB, Context: 8K, License: cc-by-nc-nd-4.0, LLM Explorer Score: 0.17, Arc: 67.8, HellaSwag: 87.4, MMLU: 74.8, GSM8K: 74.

  Cohere   Conversational   En   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/NLPark/AnFeng_v3_Avocet 

AnFeng V3 Avocet Benchmarks

ARC: 67.75 vs 96.7 (so35)-29.9%
HellaSwag: 87.43 vs 95.3 (gpt4)-8.3%
MMLU: 74.79 vs 88.3 (so35)-15.3%
GSM8K: 74 vs 96.4 (so35)-23.2%
LLME Score: 0.17072
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
AnFeng V3 Avocet (NLPark/AnFeng_v3_Avocet)
🌟 Advertise your project 🚀

AnFeng V3 Avocet Parameters and Internals

Model Type 
text generation
Additional Notes 
Sizes are labelled as: Nano, Leap, Pattern, Avocet, Robin, Kestrel.
Supported Languages 
Chinese (advanced), English (advanced)
Release Notes 
Version:
v3 early preview
Notes:
Released as an early preview for v3 series covering 'Shi-Ci', 'AnFeng', and 'Cecilia' LLM products.
LLM NameAnFeng V3 Avocet
Repository 🤗https://huggingface.co/NLPark/AnFeng_v3_Avocet 
Model Size35b
Required VRAM69.5 GB
Updated2026-05-26
MaintainerNLPark
Model Typecohere
Model Files  4.7 GB: 1-of-15   4.9 GB: 2-of-15   4.9 GB: 3-of-15   4.9 GB: 4-of-15   4.9 GB: 5-of-15   4.9 GB: 6-of-15   4.9 GB: 7-of-15   4.9 GB: 8-of-15   4.9 GB: 9-of-15   4.9 GB: 10-of-15   4.9 GB: 11-of-15   4.9 GB: 12-of-15   4.9 GB: 13-of-15   4.9 GB: 14-of-15   1.1 GB: 15-of-15
Supported Languagesen
Model ArchitectureCohereForCausalLM
Licensecc-by-nc-nd-4.0
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<PAD>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to AnFeng V3 Avocet

Best Alternatives
Context / RAM
Downloads
Likes
Command R 35B Writer V38K / 69.5 GB103
Creative Writer 35B Preview8K / 69.5 GB160
Frejya 0.88K / 69.5 GB120
Creative Writer V0.1 Alfa 35B8K / 69.5 GB284
...eative Writer V0.1 Charlie 35B8K / 69.5 GB330
Creative Writer V0.1 Bravo 35B8K / 69.5 GB380
35B Beta2ep8K / 69.5 GB818
35B Beta Long8K / 69.5 GB5567
...ommand R V01 Japanese Instruct8K / 69.5 GB724
Hansoldeco Aya 23 35B V0.18K / 69.5 GB101
Note: green Score (e.g. "73.2") means that the model is better than NLPark/AnFeng_v3_Avocet.

Rank the AnFeng V3 Avocet 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? 53972 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