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 DSV4Pro Thinking Distill by nerkyor

 »  All LLMs  »  nerkyor  »  Qwen3.6 35B A3B DSV4Pro Thinking Distill   URL Share it on

  33050   

Qwen3.6 35B A3B DSV4Pro Thinking Distill is an open-source language model by nerkyor. Features: 35b LLM, VRAM: 69.5GB, License: apache-2.0, LLM Explorer Score: 0.34.

  Arxiv:2203.14465   Arxiv:2210.03629   Arxiv:2304.01196   Arxiv:2307.16789   Arxiv:2310.12823   Arxiv:2501.12948   Agentic Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3...   Conversational   Distillation   En   Gguf   Moe   Mtp   Qwen3   Qwen3 5 moe   Reasoning   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Thinking   Zh
Model Card on HF 🤗: https://huggingface.co/nerkyor/Qwen3.6-35B-A3B-DSV4Pro-Thinking-Distill 

Qwen3.6 35B A3B DSV4Pro Thinking Distill Benchmarks

LLME Score: 0.34409
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 DSV4Pro Thinking Distill (nerkyor/Qwen3.6-35B-A3B-DSV4Pro-Thinking-Distill)
🌟 Advertise your project 🚀

Qwen3.6 35B A3B DSV4Pro Thinking Distill Parameters and Internals

LLM NameQwen3.6 35B A3B DSV4Pro Thinking Distill
Repository 🤗https://huggingface.co/nerkyor/Qwen3.6-35B-A3B-DSV4Pro-Thinking-Distill 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM69.5 GB
Updated2026-07-14
Maintainernerkyor
Model Typeqwen3_5_moe
Model Files  4.3 GB: 1-of-16   4.5 GB: 2-of-16   5.0 GB: 3-of-16   4.0 GB: 4-of-16   4.5 GB: 5-of-16   5.0 GB: 6-of-16   4.0 GB: 7-of-16   4.5 GB: 8-of-16   5.0 GB: 9-of-16   4.0 GB: 10-of-16   4.5 GB: 11-of-16   5.0 GB: 12-of-16   4.0 GB: 13-of-16   4.5 GB: 14-of-16   5.0 GB: 15-of-16   1.7 GB: 16-of-16   1.7 GB   2.9 GB
Supported Languagesen zh
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 35B A3B DSV4Pro Thinking Distill

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
Qwen3.6 35B A3B MLX VQ 2.6bpw0K / 11.5 GB5242
Qwen3.6 35B A3B AntiLoop NVFP40K / 21.3 GB9762
...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 nerkyor/Qwen3.6-35B-A3B-DSV4Pro-Thinking-Distill.

Rank the Qwen3.6 35B A3B DSV4Pro Thinking Distill 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