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

Agents A1 4B Kimi Preview Heretic by hotdogs

 »  All LLMs  »  hotdogs  »  Agents A1 4B Kimi Preview Heretic   URL Share it on

  38   

Agents A1 4B Kimi Preview Heretic is an open-source language model by hotdogs. Features: 4b LLM, VRAM: 8.4GB, Context: 256K, License: agpl-3.0, LLM Explorer Score: 0.28.

  Abliterated   Agents   Agents-a1 Base model:finetune:hotdogs/ag... Base model:hotdogs/agents-a1-4...   Chatml   Coding   Conversational Dataset:greghavens/kimi-k3-cod...   En   Endpoints compatible   Function-calling   Heretic   Kimi   Preview   Qwen   Qwen3 5 text   Reasoning   Region:us   Safetensors   Sft   Sharded   Tensorflow   Th   Tool-call   Tool-use   Uncensored
Model Card on HF 🤗: https://huggingface.co/hotdogs/Agents-A1-4B-kimi-Preview-heretic 

Agents A1 4B Kimi Preview Heretic Benchmarks

LLME Score: 0.2821
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Agents A1 4B Kimi Preview Heretic (hotdogs/Agents-A1-4B-kimi-Preview-heretic)

Agents A1 4B Kimi Preview Heretic Parameters and Internals

LLM NameAgents A1 4B Kimi Preview Heretic
Repository 🤗https://huggingface.co/hotdogs/Agents-A1-4B-kimi-Preview-heretic 
Base Model(s)  hotdogs/Agents-A1-4B-kimi-Preview   hotdogs/Agents-A1-4B-kimi-Preview
Model Size4b
Required VRAM8.4 GB
Updated2026-07-30
Maintainerhotdogs
Model Typeqwen3_5_text
Model Files  5.0 GB: 1-of-2   3.4 GB: 2-of-2
Supported Languagesen th
Model ArchitectureQwen3_5ForCausalLM
Licenseagpl-3.0
Context Length262144
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size248320
Errorsreplace

Best Alternatives to Agents A1 4B Kimi Preview Heretic

Best Alternatives
Context / RAM
Downloads
Likes
Agents A1 4B Fable Preview256K / 8.4 GB1030
Qwen35 4B Soyuz Merged256K / 8.4 GB12313
Qwen3.5 4B EU256K / 9.7 GB4740
Retrico Lm 4B Finetuned V4256K / 0 GB1430
Holo 3.1 4B Coder256K / 16.8 GB411
Qwen3.5 4B INT8256K / 4.8 GB1112
Distil Qwen35 4B256K / 8.4 GB2222
...n3.5 4B Ru Norm Link Extractor256K / 8.4 GB140
Qwen3.5 4B Ru Json Extractor256K / 8.4 GB70
Qwen3.5 4B INT8256K / 4.8 GB212
Note: green Score (e.g. "73.2") means that the model is better than hotdogs/Agents-A1-4B-kimi-Preview-heretic.

Rank the Agents A1 4B Kimi Preview Heretic 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? 55501 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer