QW

QwenPaw Flash 35B A3B Q4 K M

QwenGGUF by agentscope-aiUpdated 2026-10-08
Download on Hugging Face
Parameters34.7B
Context256K
Layers40
Architectureqwen35moe
Smallest quant21.2 GB
Quick answer

QwenPaw Flash 35B A3B Q4 K M needs about 22.3 GB of memory at Q4_K_M (a 21.2 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 2.7 GB.

QwenPaw Flash 35B A3B Q4_K_M – a 34.7B parameter mixture-of-experts model

QwenPaw Flash 35B A3B Q4_K_M is a 34.7B parameter LLM with 3B active experts. It supports 262,144 context tokens and is optimized for reasoning and tool use. The model is released under Apache‑2.0.

Good at

  • Reasoning
  • Tool integration
  • Large context handling

Limits

  • No vision support
  • Requires 22.3 GB VRAM at 8 k context
  • No benchmark data

Best for

  • Chatbots needing long context
  • Complex reasoning tasks
  • Tool‑enabled workflows

Who it’s for. Developers building AI assistants that require deep reasoning and tool usage. Suitable for projects that can allocate sufficient GPU memory and need a large‑context model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M21.2 GB 22.3 GB
Too big Get file →

The only available quant is Q4_K_M, 21.17 GB. It needs about 22.3 GB VRAM at 8 k context. For 8 GB VRAM, this model is not feasible. For 16 GB VRAM, it may run with reduced context or off‑load techniques.

What GPU do you need for QwenPaw Flash 35B A3B Q4 K M?

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 Q4_K_M (21.2 GB file, about 22.3 GB in use).

Which QwenPaw Flash 35B A3B Q4 K M quant should you choose?

Q4_K_M is the usual starting point for QwenPaw Flash 35B A3B Q4 K M: it balances file size and quality well. Here it is a 21.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters34.7B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized byagentscope-ai
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,430
Last updated2026-10-08

Frequently asked questions about QwenPaw Flash 35B A3B Q4 K M

How much VRAM does QwenPaw Flash 35B A3B Q4 K M need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 21.2 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 35B A3B Q4 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of QwenPaw Flash 35B A3B Q4 K M GGUF?

It depends on the quant: Q4_K_M is 21.2 GB.

What context length does QwenPaw Flash 35B A3B Q4 K M support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download QwenPaw Flash 35B A3B Q4 K M GGUF?

The files are on Hugging Face in the agentscope-ai/QwenPaw-Flash-35B-A3B-Q4_K_M 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 35B A3B Q4 K M 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?

No, the model requires approximately 22.3 GB VRAM at 8 k context.

What license does it use?

Apache‑2.0.

Does it support vision?

No, it has no vision capability.

Similar models

Browse all →

More from agentscope-ai

All by agentscope-ai →

More Qwen models

All Qwen →

Other large models

All large models →