What are the hardware requirements for Qwen3.6 VL REAP 26B A3B?

Qwen3.6 VL REAP 26B A3B requires approximately 53.2 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 VL REAP 26B A3B and how large is it?

Qwen3.6 VL REAP 26B A3B is developed by atbender, a model with 26.6b 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 VL REAP 26B A3B?

Qwen3.6 VL REAP 26B A3B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.6 VL REAP 26B A3B by atbender — VRAM 53.2GB, 256K context

Name: Qwen3.6 VL REAP 26B A3B
Author: atbender

Qwen3.6 VL REAP 26B A3B is an open-source language model by atbender. Features: 26.6b LLM, VRAM: 53.2GB, Context: 256K, License: apache-2.0, MoE, LLM Explorer Score: 0.24.

Arxiv:2503.02138 Agentic-coding Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.6-35b-a3... Conversational Endpoints compatible Mixture-of-experts Moe Multimodal Pruned Qwen3.6 Qwen3 5 moe text Reap Region:us Safetensors Sharded Tensorflow Vision Vision-language

Model Card on HF 🤗: https://huggingface.co/atbender/Qwen3.6-VL-REAP-26B-A3B

Qwen3.6 VL REAP 26B A3B Parameters and Internals

LLM Name	Qwen3.6 VL REAP 26B A3B
Repository 🤗	https://huggingface.co/atbender/Qwen3.6-VL-REAP-26B-A3B
Base Model(s)	Qwen/Qwen3.6-35B-A3B Qwen/Qwen3.6-35B-A3B
Model Size	26.6b
Required VRAM	53.2 GB
Updated	2026-06-25
Maintainer	atbender
Model Type	qwen3_5_moe_text
Model Files	49.8 GB: 1-of-2 3.4 GB: 2-of-2
Model Architecture	Qwen3_5MoeForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.6.0.dev0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
Errors	replace

Rank the Qwen3.6 VL REAP 26B A3B 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