LLM EXPLORER 56,604 MODELS INDEXED

Qwen3.6 35B A3B DSV4Pro Thinking Distill by nerkyor

By nerkyor · 3987 downloads
HF Repo ↗ Copy URL

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: 0.3.

  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 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
Updated2026-08-05
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 A3B0K / 72.2 GB55408552648
KAT Coder V2.5 Dev0K / 69.7 GB17885537
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
XYZ Aquila Mini0K / 70.2 GB1760432
BTL 40K / 69.9 GB57174
Qwen3.6 35B A3B Escha W20K / 12.3 GB3622236
Qwen3.6 35B A3B Abliterated V20K / 70.2 GB6219
BigBang V10K / 71.5 GB15484
...e 4.7 Opus Reasoning Distilled0K / 72.2 GB28687194
GRM 3.2 Sky0K / 70.4 GB71731
Note: green Score (e.g. "73.2") means that the model is better than nerkyor/Qwen3.6-35B-A3B-DSV4Pro-Thinking-Distill.