What are the hardware requirements for Qwen3.6 28B?

Qwen3.6 28B requires approximately 56.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.6 28B and how large is it?

Qwen3.6 28B is developed by 0xSero, a model with 35b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen3.6 28B?

Qwen3.6 28B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.6 28B by 0xSero — VRAM 56.5GB

Name: Qwen3.6 28B
Author: 0xSero

Qwen3.6 28B is an open-source language model by 0xSero. Features: 35b LLM, VRAM: 56.5GB, License: apache-2.0, LLM Explorer Score: 0.24.

Arxiv:2510.13999 Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.6-35b-a3... Conversational Endpoints compatible Expert-pruning Mixture-of-experts Pruned Qwen3.6 Qwen3 5 moe Reap Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/0xSero/Qwen3.6-28B

Qwen3.6 28B Parameters and Internals

LLM Name	Qwen3.6 28B
Repository 🤗	https://huggingface.co/0xSero/Qwen3.6-28B
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	56.5 GB
Updated	2026-09-16
Maintainer	0xSero
Model Type	qwen3_5_moe
Model Files	49.7 GB: 1-of-2 6.8 GB: 2-of-2
Model Architecture	Qwen3_5MoeForCausalLM
License	apache-2.0
Model Max Length	262144
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3.6 28B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Qwen3.6 28B

Best Alternatives	Context / RAM	Downloads	Likes
TripleTrouble V3	256K / 69.7 GB	633	2
TripleTrouble	256K / 69.7 GB	290	4
Qwen 35B A3B SignOfFour Coder	256K / 70.6 GB	1722	3
SignOfFour	256K / 70.6 GB	728	1
UltiMerge	256K / 69.3 GB	557	2
DAOS Fusion	256K / 69.3 GB	34	2
Qwen3.6 35B A3B RFT	256K / 69.3 GB	13	0
Qwen AgentWorld 35B A3B OQ4	0K / 20.3 GB	2293	7
Ornstein3.6 35B A3B RYS SABER	256K / 71 GB	179	9
...till 35B A3B Coder Abliterated	256K / 12.3 GB	43572	15

Note: green Score (e.g. "73.2") means that the model is better than 0xSero/Qwen3.6-28B.