GI

Ai sage.GigaChat3 10B A1.8B Bf16

GigachatGGUF by DevQuasarUpdated 2025-11-28
Download on Hugging Face
Parameters10.7B
Context256K
Layers26
Architecturedeepseek2
Smallest quant4.0 GB
Quick answer

Ai sage.GigaChat3 10B A1.8B Bf16 needs about 7.4 GB of memory at BF16 (a 6.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.0 GB (BF16) to 11.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Ai sage.GigaChat3 10B A1.8B Bf16 is a 10.7B-parameter Gigachat model in GGUF format, quantized by DevQuasar. Its trained context length is 256K tokens. The repository has 6 quant files, from 4.0 GB (BF16) to 11.4 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF164.0 GB 4.9 GB
Fits Get file →
BF165.1 GB 6.1 GB
Fits Get file →
BF166.5 GB 7.4 GB
Tight Get file →
BF167.6 GB 8.6 GB
Too big Get file →
BF168.8 GB 9.7 GB
Too big Get file →
BF1611.4 GB 12.3 GB
Too big Get file →

What GPU do you need for Ai sage.GigaChat3 10B A1.8B 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: the best quant that fits is BF16 (4.0 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (6.5 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.8 GB file, about 9.7 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (11.4 GB file, about 12.3 GB in use).

Which Ai sage.GigaChat3 10B A1.8B Bf16 quant should you choose?

BF16 (6.5 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.

If memory is tight, the smallest file is BF16 at 4.0 GB, with the quality trade-offs that come with fewer bits. 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

Architecturedeepseek2
Parameters10.7B (approximate, mixture of experts)
Active parameters1.8B
Layers26
Trained context262,144 tokens
KV cache (fp16)55 KB per token

Source

Quantized byDevQuasar
FamilyGigachat
Licensemit
Downloads (HF)110
Last updated2025-11-28

Frequently asked questions about Ai sage.GigaChat3 10B A1.8B Bf16

How much VRAM does Ai sage.GigaChat3 10B A1.8B Bf16 need?

About 7.4 GB at BF16 with an 8K context window. That is the 6.5 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 Ai sage.GigaChat3 10B A1.8B Bf16 on an 8 GB GPU?

Yes, with BF16: the 6.5 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ai sage.GigaChat3 10B A1.8B Bf16 GGUF?

It depends on the quant: BF16 is 4.0 GB, BF16 is 5.1 GB, BF16 is 6.5 GB, BF16 is 7.6 GB, BF16 is 8.8 GB, BF16 is 11.4 GB.

What context length does Ai sage.GigaChat3 10B A1.8B 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 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Ai sage.GigaChat3 10B A1.8B Bf16 GGUF?

The files are on Hugging Face in the DevQuasar/ai-sage.GigaChat3-10B-A1.8B-bf16-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 Ai sage.GigaChat3 10B A1.8B Bf16 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 GigaChat3-10B-A1.8B-bf16

Similar models

Browse all →

More from DevQuasar

All by DevQuasar →

More Gigachat models

All Gigachat →

Other medium models

All medium models →