QW

Qwen3.5 Thinking AIO

QwenGGUF by prithivMLmodsUpdated 2026-03-12
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.8 GB
Quick answer

Qwen3.5 Thinking AIO needs about 5.4 GB of memory at Q8_0 (a 4.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 16 quants, from 0.8 GB (Q8_0) to 35.8 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Qwen3.5 Thinking AIO – 0.8B parameter model with reasoning, tools, and vision

Qwen3.5 Thinking AIO is a 0.8B parameter language model based on the Qwen family. It supports reasoning, tools, and vision tasks. The model is released under the apache-2.0 license and is intended for research and learning.

Good at

  • Reasoning
  • Tool use
  • Vision

Limits

  • No safety alignment – may produce unrestricted content
  • Requires 8k context for memory estimates
  • No official benchmarks provided

Best for

  • Research on multimodal reasoning
  • Dataset generation with uncensored outputs
  • Edge deployment with low VRAM

Who it’s for. Researchers and developers needing a lightweight, unrestricted Qwen3.5 variant for experimentation. The model is suitable for those who can handle potential safety risks and want to explore advanced reasoning and vision capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.8 GB 1.7 GB
Fits Get file →
BF161.5 GB 2.4 GB
Fits Get file →
F161.5 GB 2.4 GB
Fits Get file →
Q8_02.0 GB 2.9 GB
Fits Get file →
F323.0 GB 3.9 GB
Fits Get file →
BF163.8 GB 4.7 GB
Fits Get file →
F163.8 GB 4.7 GB
Fits Get file →
Q8_04.5 GB 5.4 GB
Fits Get file →
F327.5 GB 8.4 GB
Too big Get file →
BF168.4 GB 9.3 GB
Too big Get file →
F168.4 GB 9.3 GB
Too big Get file →
Q8_09.5 GB 10.4 GB
Too big Get file →
F3216.8 GB 17.7 GB
Too big Get file →
BF1617.9 GB 18.8 GB
Too big Get file →
F1617.9 GB 18.8 GB
Too big Get file →
F3235.8 GB 36.7 GB
Too big Get file →

For 8GB VRAM use the Q8_0 quant at 0.81GB file size, which needs about 1.7GB memory at 8k context. If more memory is available, the F16 quant at 1.52GB file size requires about 2.4GB. Larger quants such as F32 at 3.02GB need roughly 3.9GB memory.

What GPU do you need for Qwen3.5 Thinking AIO?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F32 (3.0 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 5.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 10.4 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 18.8 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 18.8 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (35.8 GB file, about 36.7 GB in use).

Which Qwen3.5 Thinking AIO quant should you choose?

Q8_0 (4.5 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q8_0 at 0.8 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byprithivMLmods
FamilyQwen
Licenseapache-2.0
Downloads (HF)745
Last updated2026-03-12

Frequently asked questions about Qwen3.5 Thinking AIO

How much VRAM does Qwen3.5 Thinking AIO need?

About 5.4 GB at Q8_0 with an 8K context window. That is the 4.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen3.5 Thinking AIO on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5 Thinking AIO GGUF?

It depends on the quant: Q8_0 is 0.8 GB, BF16 is 1.5 GB, F16 is 1.5 GB, Q8_0 is 2.0 GB, F32 is 3.0 GB, BF16 is 3.8 GB and 10 more.

What context length does Qwen3.5 Thinking AIO support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Qwen3.5 Thinking AIO GGUF?

The files are on Hugging Face in the prithivMLmods/Qwen3.5-Thinking-AIO-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen3.5 Thinking AIO use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the Q8_0 quant file of 0.81GB requires about 1.7GB memory at 8k context, fitting within 8GB VRAM.

Does this model support vision tasks?

Yes, the model has detected vision ability and can process image inputs.

Is the model safe for production use?

No, it is intended for research only and may produce unrestricted content due to lack of safety alignment.

Other GGUFs of Qwen3.5-0.8B-Unredacted-MAX

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Qwen models

All Qwen →

Other tiny models

All tiny models →