CA

G9v3 39A5B

CafepmGGUF by cafepmUpdated 2026-09-05
Download on Hugging Face
Parameters39B
Context128K
Layers38
Architecturedeepseek2
Smallest quant15.1 GB
Quick answer

G9v3 39A5B needs about 20.2 GB of memory at its main file (a 19.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 15.1 GB to 24.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.3 GB.

G9v3 39A5B is a 39B-parameter Cafepm model in GGUF format, quantized by cafepm. Its trained context length is 128K tokens. The repository has 3 quant files, from 15.1 GB to 24.1 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—15.1 GB 16.0 GB
Too big Get file →
—19.4 GB 20.2 GB
Too big Get file →
—24.1 GB 24.9 GB
Too big Get file →

What GPU do you need for G9v3 39A5B?

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: the best quant that fits is the main file (15.1 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (19.4 GB file, about 20.2 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (24.1 GB file, about 24.9 GB in use).

Which G9v3 39A5B quant should you choose?

If memory is tight, the smallest file is the first one in the table at 15.1 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

Architecturedeepseek2
Parameters39B (approximate, mixture of experts)
Layers38
Trained context131,072 tokens
KV cache (fp16)38 KB per token

Source

Quantized bycafepm
FamilyCafepm
Licenseapache-2.0
Downloads (HF)104
Last updated2026-09-05

Frequently asked questions about G9v3 39A5B

How much VRAM does G9v3 39A5B need?

About 20.2 GB at its main file with an 8K context window. That is the 19.4 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 G9v3 39A5B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of G9v3 39A5B GGUF?

It depends on the quant: file is 15.1 GB, file is 19.4 GB, file is 24.1 GB.

What context length does G9v3 39A5B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.3 GB at 32K.

Where can I download G9v3 39A5B GGUF?

The files are on Hugging Face in the cafepm/G9v3-39A5B-Q3Q4-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 G9v3 39A5B 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 cafepm

All by cafepm →

Other large models

All large models →