What are the hardware requirements for Qwen3.6 35B A3B DFlash2?

Qwen3.6 35B A3B DFlash2 requires approximately 1.1 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.6 35B A3B DFlash2 and how large is it?

Qwen3.6 35B A3B DFlash2 is developed by incoai, 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 35B A3B DFlash2?

Qwen3.6 35B A3B DFlash2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.6 35B A3B DFlash2 by incoai — VRAM 1.1GB, 256K context

Name: Qwen3.6 35B A3B DFlash2
Author: incoai

Qwen3.6 35B A3B DFlash2 is an open-source language model by incoai. Features: 35b LLM, VRAM: 1.1GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.31.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.6-35b-a3... Block-diffusion Dflash2 Draft-model Qwen3 Region:us Safetensors Sglang Speculative-decoding Vllm

Model Card on HF 🤗: https://huggingface.co/incoai/Qwen3.6-35B-A3B-DFlash2

Qwen3.6 35B A3B DFlash2 Parameters and Internals

LLM Name	Qwen3.6 35B A3B DFlash2
Repository 🤗	https://huggingface.co/incoai/Qwen3.6-35B-A3B-DFlash2
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	1.1 GB
Updated	2026-09-26
Maintainer	incoai
Model Type	qwen3
Model Files	1.1 GB
Model Architecture	DFlash2DraftModel
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.7.0
Vocabulary Size	248320

Rank the Qwen3.6 35B A3B DFlash2 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 35B A3B DFlash2

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.6 35B A3B DFlash2 4bit	256K / 0.5 GB	650	5

Note: green Score (e.g. "73.2") means that the model is better than incoai/Qwen3.6-35B-A3B-DFlash2.