QW

QwenPaw Flash 9B

QwenGGUF by agentscope-aiUpdated 2026-10-09
Download on Hugging Face
Parameters8.95B
Context256K
Layers32
Architectureqwen35
Smallest quant17.9 GB
Quick answer

QwenPaw Flash 9B needs about 19.5 GB of memory at BF16 (a 17.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

QwenPaw Flash 9B – lightweight agent‑optimized Qwen model

QwenPaw Flash 9B is a 9B‑parameter causal language model fine‑tuned for QwenPaw autonomous agents. It excels at reasoning, tool invocation, and multi‑step planning. The model is released under the Apache‑2.0 license.

Good at

  • Reasoning
  • Tool invocation
  • Multi‑step planning

Limits

  • Requires ~19.5 GB VRAM at 8 k context
  • Large context length of 262,144 tokens
  • No vision support specified

Best for

  • Building autonomous agents
  • Generating precise CLI commands
  • Web‑search tool integration

Who it’s for. Developers and teams creating QwenPaw‑based agents who need efficient, agent‑centric language capabilities. The model is suitable for applications that demand high logical consistency and tool‑based interactions.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1617.9 GB 19.5 GB
Too big Get file →

The only available quantization is BF16, with a file size of 17.92 GB and an estimated VRAM usage of 19.5 GB at 8 k context. This is the recommended quant for systems with at least 20 GB of VRAM. For lower‑budget setups, no other quants are provided.

What GPU do you need for QwenPaw Flash 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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 GB in use).

Which QwenPaw Flash 9B quant should you choose?

BF16 (17.9 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 byagentscope-ai
FamilyQwen
Base modelQwen/Qwen3.5-9B
Licenseapache-2.0
Downloads (HF)897
Last updated2026-10-09

Frequently asked questions about QwenPaw Flash 9B

How much VRAM does QwenPaw Flash 9B need?

About 19.5 GB at BF16 with an 8K context window. That is the 17.9 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 QwenPaw Flash 9B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of QwenPaw Flash 9B GGUF?

It depends on the quant: BF16 is 17.9 GB.

What context length does QwenPaw Flash 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 4.3 GB at 32K.

Where can I download QwenPaw Flash 9B GGUF?

The files are on Hugging Face in the agentscope-ai/QwenPaw-Flash-9B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does QwenPaw Flash 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 QwenPaw Flash 9B on 8 GB VRAM?

No, the BF16 quant requires approximately 19.5 GB of VRAM at 8 k context.

Is the model compatible with CPU inference?

The provided GGUF file is optimized for GPU inference; CPU usage is not documented.

Other GGUFs of Qwen3.5-9B

Similar models

Browse all →

More from agentscope-ai

All by agentscope-ai →

More Qwen models

All Qwen →

Other small models

All small models →