AU

MS3.2 Austral Winton

AustralGGUF by CarnyzzleUpdated 2025-07-02
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant16.8 GB
Quick answer

MS3.2 Austral Winton needs about 18.6 GB of memory at Q5_K_M (a 16.8 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 5.4 GB.

MS3.2 Austral Winton is a 23.6B-parameter Austral model in GGUF format, quantized by Carnyzzle. Its trained context length is 128K tokens. The repository has 1 quant file, from 16.8 GB (Q5_K_M) to 16.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M16.8 GB 18.6 GB
Too big Get file →

What GPU do you need for MS3.2 Austral Winton?

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 Q5_K_M (16.8 GB file, about 18.6 GB in use).

Which MS3.2 Austral Winton quant should you choose?

Q5_K_M (16.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byCarnyzzle
FamilyAustral
Licenseapache-2.0
Downloads (HF)34
Last updated2025-07-02

Frequently asked questions about MS3.2 Austral Winton

How much VRAM does MS3.2 Austral Winton need?

About 18.6 GB at Q5_K_M with an 8K context window. That is the 16.8 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 MS3.2 Austral Winton on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MS3.2 Austral Winton GGUF?

It depends on the quant: Q5_K_M is 16.8 GB.

What context length does MS3.2 Austral Winton support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download MS3.2 Austral Winton GGUF?

The files are on Hugging Face in the Carnyzzle/MS3.2-Austral-Winton-Q5_K_M-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 MS3.2 Austral Winton 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 MS3.2-Austral-Winton

Similar models

Browse all →

More from Carnyzzle

All by Carnyzzle →

More Austral models

All Austral →

Other medium models

All medium models →