GI

GigaChat 20B A3B instruct Q4 K S

GigachatGGUF by NikolayKozloffUpdated 2024-12-18
Download on Hugging Face
Parameters20.6B
Context128K
Layers—
Architecturedeepseek
Smallest quant11.7 GB
Quick answer

GigaChat 20B A3B instruct Q4 K S needs about 13.6 GB of memory at Q4_K_S (a 11.7 GB file) with an 8K context window, so it fits on a 16 GB GPU.

GigaChat 20B A3B instruct Q4 K S is a 20.6B-parameter Gigachat model in GGUF format, quantized by NikolayKozloff. Its trained context length is 128K tokens. The repository has 1 quant file, from 11.7 GB (Q4_K_S) to 11.7 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S11.7 GB 13.6 GB
Too big Get file →

What GPU do you need for GigaChat 20B A3B instruct Q4 K S?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q4_K_S (11.7 GB file, about 13.6 GB in use).

Which GigaChat 20B A3B instruct Q4 K S quant should you choose?

Q4_K_S (11.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek
Parameters20.6B
Trained context131,072 tokens

Source

Quantized byNikolayKozloff
FamilyGigachat
Licensemit
Downloads (HF)18
Last updated2024-12-18

Frequently asked questions about GigaChat 20B A3B instruct Q4 K S

How much VRAM does GigaChat 20B A3B instruct Q4 K S need?

About 13.6 GB at Q4_K_S with an 8K context window. That is the 11.7 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 GigaChat 20B A3B instruct Q4 K S on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GigaChat 20B A3B instruct Q4 K S GGUF?

It depends on the quant: Q4_K_S is 11.7 GB.

What context length does GigaChat 20B A3B instruct Q4 K S support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download GigaChat 20B A3B instruct Q4 K S GGUF?

The files are on Hugging Face in the NikolayKozloff/GigaChat-20B-A3B-instruct-Q4_K_S-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 GigaChat 20B A3B instruct Q4 K S use?

Hugging Face lists the license as mit. 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 GigaChat-20B-A3B-instruct

Similar models

Browse all →

More from NikolayKozloff

All by NikolayKozloff →

More Gigachat models

All Gigachat →

Other medium models

All medium models →