QW

Qwen3.5-9B

QwenGGUF by EcoAI-LabUpdated 2026-10-23
Download on Hugging Face
Parameters9.2B
Context256K
Layers33
Architectureqwen35
Smallest quant3.9 GB
Quick answer

Qwen3.5-9B needs about 6.0 GB of memory at its main file (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 3.9 GB to 5.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

Qwen3.5‑9B: 9.2B‑parameter causal model with vision encoder

Qwen3.5‑9B is a 9.2B‑parameter causal language model that includes a vision encoder. It supports 262,144‑token context length and is trained on 201 languages. The model is released under the Apache‑2.0 license.

Good at

  • Large‑context text generation
  • Vision‑language reasoning
  • Multilingual support

Limits

  • Requires patched llama.cpp for quant files
  • Large VRAM needed for full precision
  • No separate quant types listed

Best for

  • Chatbots needing long context
  • Vision‑language agents
  • Multilingual content creation

Who it’s for. Developers building agents or chat systems that need extended context and vision capabilities. The model is suitable for research and production environments that can accommodate its memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—3.9 GB 5.5 GB
Fits Get file →
—4.1 GB 5.7 GB
Fits Get file →
—4.4 GB 6.0 GB
Fits Get file →
—4.8 GB 6.4 GB
Fits Get file →
—5.1 GB 6.7 GB
Fits Get file →

For 8 GB VRAM, use the 4.07 GB file (est. 5.7 GB memory at 8 k context). For 12 GB VRAM, the 5.1 GB file (est. 6.7 GB memory) is suitable. Larger VRAM allows the 4.76 GB file (est. 6.4 GB memory).

What GPU do you need for Qwen3.5-9B?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is the main file (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (5.1 GB file, about 6.7 GB in use).

Which Qwen3.5-9B quant should you choose?

If memory is tight, the smallest file is the first one in the table at 3.9 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters9.2B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized byEcoAI-Lab
FamilyQwen
Base modelQwen/Qwen3.5-9B
Licenseapache-2.0
Downloads (HF)2,365
Last updated2026-10-23

Frequently asked questions about Qwen3.5-9B

How much VRAM does Qwen3.5-9B need?

About 6.0 GB at its main file with an 8K context window. That is the 4.4 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 Qwen3.5-9B on an 8 GB GPU?

Yes, with the smaller files: the 5.1 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3.5-9B GGUF?

It depends on the quant: file is 3.9 GB, file is 4.1 GB, file is 4.4 GB, file is 4.8 GB, file is 5.1 GB.

What context length does Qwen3.5-9B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download Qwen3.5-9B GGUF?

The files are on Hugging Face in the EcoAI-Lab/ShiftAddQwen-3.5-9B-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 Qwen3.5-9B 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 Qwen3.5‑9B on 8 GB VRAM?

Yes, the 4.07 GB quant file uses about 5.7 GB of VRAM at 8 k context, which fits in 8 GB.

Do I need a patched llama.cpp to use the quant files?

Yes, the quant files require a patched llama.cpp that supports the ShiftAddLLM weight representation.

Is there a vision‑only mode for this model?

The model includes a vision encoder, but it is designed for combined vision‑language tasks, not a separate vision‑only mode.

Other GGUFs of Qwen3.5-9B

Similar models

Browse all →

More Qwen models

All Qwen →

Other small models

All small models →