LLM EXPLORER 62,233 MODELS INDEXED

Qwen3.6 27B DSV4Pro Thinking Distill NVFP4 by nerkyor

By nerkyor · 666 downloads
HF Repo ↗ Copy URL

Qwen3.6 27B DSV4Pro Thinking Distill NVFP4 is an open-source language model by nerkyor. Features: 27b LLM, VRAM: 30.1GB, License: apache-2.0, LLM Explorer Score: 0.27.

Base model:nerkyor/qwen3.6-27b... Base model:quantized:nerkyor/q...   Conversational   Distillation   En   Modelopt   Mtp   Nvfp4   Quantization   Qwen3   Qwen3 5   Reasoning   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Thinking   Vllm   Zh
Model Card on HF 🤗: https://huggingface.co/nerkyor/Qwen3.6-27B-DSV4Pro-Thinking-Distill-NVFP4 

Qwen3.6 27B DSV4Pro Thinking Distill NVFP4 Parameters and Internals

LLM NameQwen3.6 27B DSV4Pro Thinking Distill NVFP4
Repository 🤗https://huggingface.co/nerkyor/Qwen3.6-27B-DSV4Pro-Thinking-Distill-NVFP4 
Base Model(s)  nerkyor/Qwen3.6-27B-DSV4Pro-Thinking-Distill   nerkyor/Qwen3.6-27B-DSV4Pro-Thinking-Distill
Model Size27b
Required VRAM30.1 GB
Updated2026-07-19
Maintainernerkyor
Model Typeqwen3_5
Model Files  8.0 GB: 1-of-4   8.0 GB: 2-of-4   7.9 GB: 3-of-4   6.2 GB: 4-of-4   0.8 GB
Supported Languagesen zh
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.5.4
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 27B DSV4Pro Thinking Distill NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB1721
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.5 27B0K / 55.2 GB25362941028
Qwen3.6 27B FP80K / 0.4 GB7740472342
Note: green Score (e.g. "73.2") means that the model is better than nerkyor/Qwen3.6-27B-DSV4Pro-Thinking-Distill-NVFP4.