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

Qwen3.6 35B A3B AntiLoop NVFP4 by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen3.6 35B A3B AntiLoop NVFP4   URL Share it on

  976   

Qwen3.6 35B A3B AntiLoop NVFP4 is an open-source language model by mlx-community. Features: 35b LLM, VRAM: 21.3GB, License: apache-2.0, LLM Explorer Score: 0.33.

  Antidoom Base model:adapter:n8programs/... Base model:n8programs/qwen3.6-...   Conversational   Fp4   Fp8   Lora   Merge   Mlx   Mlx-lm   Modelopt   Moe   Nvfp4   Quantized   Qwen3.6   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-AntiLoop-NVFP4 

Qwen3.6 35B A3B AntiLoop NVFP4 Benchmarks

LLME Score: 0.33273
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3.6 35B A3B AntiLoop NVFP4 (mlx-community/Qwen3.6-35B-A3B-AntiLoop-NVFP4)
🌟 Advertise your project 🚀

Qwen3.6 35B A3B AntiLoop NVFP4 Parameters and Internals

LLM NameQwen3.6 35B A3B AntiLoop NVFP4
Repository 🤗https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-AntiLoop-NVFP4 
Base Model(s)  nvidia/Qwen3.6-35B-A3B-NVFP4   N8Programs/Qwen3.6-35B-A3B-AntiLoop   nvidia/Qwen3.6-35B-A3B-NVFP4   N8Programs/Qwen3.6-35B-A3B-AntiLoop
Model Size35b
Required VRAM21.3 GB
Updated2026-07-14
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  1.3 GB: 1-of-41   0.5 GB: 2-of-41   0.5 GB: 3-of-41   0.5 GB: 4-of-41   0.5 GB: 5-of-41   0.5 GB: 6-of-41   0.5 GB: 7-of-41   0.5 GB: 8-of-41   0.5 GB: 9-of-41   0.5 GB: 10-of-41   0.5 GB: 11-of-41   0.5 GB: 12-of-41   0.5 GB: 13-of-41   0.5 GB: 14-of-41   0.5 GB: 15-of-41   0.5 GB: 16-of-41   0.5 GB: 17-of-41   0.5 GB: 18-of-41   0.5 GB: 19-of-41   0.5 GB: 20-of-41   0.5 GB: 21-of-41   0.5 GB: 22-of-41   0.5 GB: 23-of-41   0.5 GB: 24-of-41   0.5 GB: 25-of-41   0.5 GB: 26-of-41   0.5 GB: 27-of-41   0.5 GB: 28-of-41   0.5 GB: 29-of-41   0.5 GB: 30-of-41   0.5 GB: 31-of-41   0.5 GB: 32-of-41   0.5 GB: 33-of-41   0.5 GB: 34-of-41   0.5 GB: 35-of-41   0.5 GB: 36-of-41   0.5 GB: 37-of-41   0.5 GB: 38-of-41   0.5 GB: 39-of-41   0.5 GB: 40-of-41   0.5 GB: 41-of-41
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Transformers Version5.7.0.dev0

Best Alternatives to Qwen3.6 35B A3B AntiLoop NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B NVFP40K / 23.4 GB4812629361
Qwen3.6 35B A3B Abliterated V20K / 70.2 GB6189
...e 4.7 Opus Reasoning Distilled0K / 72.2 GB28687194
...B A3B PrismaQuant 4.75bit Vllm0K / 23 GB10521032
...B A3B DSV4Pro Thinking Distill0K / 69.5 GB330508
Qwen3.6 35B A3B MLX VQ 2.6bpw0K / 11.5 GB5242
...s Pentester BugHunter RATH Mlx0K / 69.1 GB484927
Qwen3.6 35B A3B NVFP40K / 25.6 GB499269
Qwen3.6 35B A3B PRISM NVFP40K / 1.7 GB2766120
Qwen3.6 35B A3B StyleTune0K / 70.2 GB17327
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.6-35B-A3B-AntiLoop-NVFP4.

Rank the Qwen3.6 35B A3B AntiLoop NVFP4 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? 55092 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