FU

Fuse 2 MoE BF16

FuseGGUF by AkahsizrrUpdated 2026-08-30
Download on Hugging Face
Parameters8.87B
Context256K
Layers32
Architectureqwen35moe
Smallest quant17.8 GB
Quick answer

Fuse 2 MoE BF16 needs about 19.3 GB of memory at BF16 (a 17.8 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.

Fuse 2 MoE BF16 is a 8.87B-parameter Fuse model in GGUF format, quantized by Akahsizrr. Its trained context length is 256K tokens. The repository has 1 quant file, from 17.8 GB (BF16) to 17.8 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1617.8 GB 19.3 GB
Too big Get file →

What GPU do you need for Fuse 2 MoE BF16?

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 (17.8 GB file, about 19.3 GB in use).

Which Fuse 2 MoE BF16 quant should you choose?

BF16 (17.8 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

Architectureqwen35moe
Parameters8.87B (approximate, mixture of experts)
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byAkahsizrr
FamilyFuse
Licenseapache-2.0
Downloads (HF)53
Last updated2026-08-30

Frequently asked questions about Fuse 2 MoE BF16

How much VRAM does Fuse 2 MoE BF16 need?

About 19.3 GB at BF16 with an 8K context window. That is the 17.8 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 Fuse 2 MoE BF16 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Fuse 2 MoE BF16 GGUF?

It depends on the quant: BF16 is 17.8 GB.

What context length does Fuse 2 MoE BF16 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 Fuse 2 MoE BF16 GGUF?

The files are on Hugging Face in the Akahsizrr/Fuse-2-MoE-BF16 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Fuse 2 MoE BF16 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 Akahsizrr

All by Akahsizrr →

More Fuse models

All Fuse →

Other small models

All small models →