AG

Agnes-3.0-Flash-Preview

AgnesGGUF by kingjones777Updated 2026-10-25
Download on Hugging Face
Parameters32.7B
Context256K
Layers73
Architectureqwen35
Smallest quant3.2 GB
Quick answer

Agnes-3.0-Flash-Preview needs about 22.0 GB of memory at Q4_0 (a 19.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 3.2 GB (Q8_0) to 34.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 9.8 GB.

Agnes-3.0-Flash-Preview is a 32.7B-parameter Agnes model in GGUF format, quantized by kingjones777. Its trained context length is 256K tokens. The repository has 5 quant files, from 3.2 GB (Q8_0) to 34.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_03.2 GB 6.1 GB
Fits Get file →
Q4_018.1 GB 21.0 GB
Too big Get file →
Q4_019.1 GB 22.0 GB
Too big Get file →
Q8_033.8 GB 36.7 GB
Too big Get file →
Q8_034.3 GB 37.2 GB
Too big Get file →

What GPU do you need for Agnes-3.0-Flash-Preview?

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: the best quant that fits is Q8_0 (3.2 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 6.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (3.2 GB file, about 6.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_0 (19.1 GB file, about 22.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_0 (19.1 GB file, about 22.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (34.3 GB file, about 37.2 GB in use).

Which Agnes-3.0-Flash-Preview quant should you choose?

Q4_0 (19.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q8_0 at 3.2 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters32.7B
Layers73
Trained context262,144 tokens
KV cache (fp16)292 KB per token

Source

Quantized bykingjones777
FamilyAgnes
Licenseapache-2.0
Downloads (HF)333
Last updated2026-10-25

Frequently asked questions about Agnes-3.0-Flash-Preview

How much VRAM does Agnes-3.0-Flash-Preview need?

About 22.0 GB at Q4_0 with an 8K context window. That is the 19.1 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 Agnes-3.0-Flash-Preview on an 8 GB GPU?

Yes, with Q8_0: the 3.2 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Agnes-3.0-Flash-Preview GGUF?

It depends on the quant: Q8_0 is 3.2 GB, Q4_0 is 18.1 GB, Q4_0 is 19.1 GB, Q8_0 is 33.8 GB, Q8_0 is 34.3 GB.

What context length does Agnes-3.0-Flash-Preview support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.4 GB at 8K and 9.8 GB at 32K.

Where can I download Agnes-3.0-Flash-Preview GGUF?

The files are on Hugging Face in the kingjones777/Agnes-3.0-Flash-Preview-MTP-ROCmFP4-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 Agnes-3.0-Flash-Preview 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.

Other GGUFs of Agnes-3.0-Flash

Similar models

Browse all →

More from kingjones777

All by kingjones777 →

More Agnes models

All Agnes →

Other medium models

All medium models →