QW

Sakura Whittle Qwen 3.8 45B A3B

QwenGGUF by webmp3Updated 2026-11-09
Download on Hugging Face
Parameters45.1B
Context256K
Layers40
Architectureqwen4exp
Smallest quant16.4 GB
Quick answer

Sakura Whittle Qwen 3.8 45B A3B needs about 28.3 GB of memory at Q4_K_M (a 27.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 16.4 GB (Q2_K) to 31.9 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Sakura Whittle Qwen 3.8 45B A3B is a 45.1B-parameter Qwen model in GGUF format, quantized by webmp3. Its trained context length is 256K tokens. The repository has 4 quant files, from 16.4 GB (Q2_K) to 31.9 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K16.4 GB 17.6 GB
Too big Get file →
Q3_K_M21.3 GB 22.5 GB
Too big Get file →
Q4_K_M27.1 GB 28.3 GB
Too big Get file →
Q5_K_M31.9 GB 33.1 GB
Too big Get file →

What GPU do you need for Sakura Whittle Qwen 3.8 45B A3B?

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 Q3_K_M (21.3 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_M (27.1 GB file, about 28.3 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_M (31.9 GB file, about 33.1 GB in use).

Which Sakura Whittle Qwen 3.8 45B A3B quant should you choose?

Q4_K_M is the usual starting point for Sakura Whittle Qwen 3.8 45B A3B: it balances file size and quality well. Here it is a 27.1 GB file.

If memory is tight, the smallest file is Q2_K at 16.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen4exp
Parameters45.1B (approximate, mixture of experts)
Active parameters3B
Layers40
Trained context262,144 tokens
KV cache (fp16)80 KB per token

Source

Quantized bywebmp3
FamilyQwen
Licenseapache-2.0
Downloads (HF)166
Last updated2026-11-09

Frequently asked questions about Sakura Whittle Qwen 3.8 45B A3B

How much VRAM does Sakura Whittle Qwen 3.8 45B A3B need?

About 28.3 GB at Q4_K_M with an 8K context window. That is the 27.1 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 Sakura Whittle Qwen 3.8 45B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sakura Whittle Qwen 3.8 45B A3B GGUF?

It depends on the quant: Q2_K is 16.4 GB, Q3_K_M is 21.3 GB, Q4_K_M is 27.1 GB, Q5_K_M is 31.9 GB.

What context length does Sakura Whittle Qwen 3.8 45B A3B 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 Sakura Whittle Qwen 3.8 45B A3B GGUF?

The files are on Hugging Face in the webmp3/Sakura-Whittle-Qwen-3.8-45B-A3B-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 Sakura Whittle Qwen 3.8 45B A3B 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.

Similar models

Browse all →

More from webmp3

All by webmp3 →

More Qwen models

All Qwen →

Other large models

All large models →