QW

Qwen3.8 Mixed NVFP4 FP8

QwenGGUF by williamliaoUpdated 2026-11-07
Download on Hugging Face
Parameters27.3B
Context256K
Layers65
Architectureqwen35
Smallest quant21.0 GB
Quick answer

Qwen3.8 Mixed NVFP4 FP8 needs about 23.7 GB of memory at its main file (a 21.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 21.0 GB to 21.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Qwen3.8 Mixed NVFP4 FP8 is a 27.3B-parameter Qwen model in GGUF format, quantized by williamliao. Its trained context length is 256K tokens. The repository has 3 quant files, from 21.0 GB to 21.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—21.0 GB 23.7 GB
Too big Get file →
—21.0 GB 23.7 GB
Too big Get file →
—21.5 GB 24.1 GB
Too big Get file →

What GPU do you need for Qwen3.8 Mixed NVFP4 FP8?

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 the main file (21.0 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (21.5 GB file, about 24.1 GB in use).

Which Qwen3.8 Mixed NVFP4 FP8 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 21.0 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
Parameters27.3B
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Frequently asked questions about Qwen3.8 Mixed NVFP4 FP8

How much VRAM does Qwen3.8 Mixed NVFP4 FP8 need?

About 23.7 GB at its main file with an 8K context window. That is the 21.0 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 Qwen3.8 Mixed NVFP4 FP8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.8 Mixed NVFP4 FP8 GGUF?

It depends on the quant: file is 21.0 GB, file is 21.0 GB, file is 21.5 GB.

What context length does Qwen3.8 Mixed NVFP4 FP8 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.

Where can I download Qwen3.8 Mixed NVFP4 FP8 GGUF?

The files are on Hugging Face in the williamliao/Qwen3.8-Mixed-NVFP4-FP8-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 Qwen3.8 Mixed NVFP4 FP8 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 williamliao

All by williamliao →

More Qwen models

All Qwen →

Other medium models

All medium models →