QW

Qwen3.5 9B BOS Q8 NonThinking

QwenGGUF by shaban2024Updated 2026-10-10
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant9.5 GB
Quick answer

Qwen3.5 9B BOS Q8 NonThinking needs about 11.1 GB of memory at its main file (a 9.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 9.5 GB to 9.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Qwen3.5 9B BOS Q8 NonThinking – 9B parameter model with vision and reasoning

Qwen3.5 9B BOS Q8 NonThinking is a 9‑billion‑parameter causal language model with vision encoder. It supports reasoning and tool use. The model is released under Apache‑2.0 and is available in GGUF format.

Good at

  • Reasoning tasks
  • Tool‑based interactions
  • Vision‑language understanding

Limits

  • No vision support in this GGUF variant
  • Requires 8‑k context for memory estimates
  • Experimental – not production ready

Best for

  • Developers building reasoning agents
  • Tool‑enabled chatbots
  • Vision‑language research prototypes

Who it’s for. This model is suitable for developers and researchers who need a 9B parameter model with reasoning and tool‑use capabilities. It is best used in experimental settings where the latest vision‑language features are required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—9.5 GB 11.1 GB
Too big Get file →
—9.5 GB 11.1 GB
Too big Get file →
—9.5 GB 11.1 GB
Too big Get file →
—9.5 GB 11.1 GB
Too big Get file →
—9.5 GB 11.1 GB
Too big Get file →
—9.5 GB 11.1 GB
Too big Get file →
—9.5 GB 11.1 GB
Too big Get file →

The provided GGUF files are 9.53 GB each and estimate 11.1 GB of VRAM at 8 k context. For systems with 12 GB VRAM, the base GGUF can run with 8 k context. For larger contexts or lower VRAM, consider quantizing to a lower precision such as Q4_K_M, which reduces file size and memory usage.

What GPU do you need for Qwen3.5 9B BOS Q8 NonThinking?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is the main file (9.5 GB file, about 11.1 GB in use).

Which Qwen3.5 9B BOS Q8 NonThinking quant should you choose?

If memory is tight, the smallest file is the first one in the table at 9.5 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
Parameters8.95B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byshaban2024
FamilyQwen
Base modelQwen/Qwen3.5-9B
Licenseapache-2.0
Downloads (HF)6,184
Last updated2026-10-10

Frequently asked questions about Qwen3.5 9B BOS Q8 NonThinking

How much VRAM does Qwen3.5 9B BOS Q8 NonThinking need?

About 11.1 GB at its main file with an 8K context window. That is the 9.5 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 9B BOS Q8 NonThinking on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.5 9B BOS Q8 NonThinking GGUF?

It depends on the quant: file is 9.5 GB, file is 9.5 GB, file is 9.5 GB, file is 9.5 GB, file is 9.5 GB, file is 9.5 GB and 1 more.

What context length does Qwen3.5 9B BOS Q8 NonThinking 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 4.3 GB at 32K.

Where can I download Qwen3.5 9B BOS Q8 NonThinking GGUF?

The files are on Hugging Face in the shaban2024/Qwen3.5-9B-BOS-Q8-NonThinking 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 BOS Q8 NonThinking 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?

The base GGUF requires about 11.1 GB VRAM at 8 k context, so 8 GB VRAM is insufficient without further quantization.

Does this model support vision tasks?

The GGUF variant described does not include vision support; it is a text‑only model.

Is this model production ready?

No, the model is marked experimental and is not recommended for production deployments.

Other GGUFs of Qwen3.5-9B

Similar models

Browse all →

More from shaban2024

All by shaban2024 →

More Qwen models

All Qwen →

Other small models

All small models →