SF

sft v1 q4km

SftGGUF by Ha-Te-21Updated 2026-10-31
Download on Hugging Face
Parameters7.46B
Context128K
Layers42
Architecturegemma4
Smallest quant5.3 GB
Quick answer

sft v1 q4km needs about 7.2 GB of memory at its main file (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

sft v1 q4km is a 7.46B-parameter Sft model in GGUF format, quantized by Ha-Te-21. Its trained context length is 128K tokens. The repository has 1 quant file, from 5.3 GB to 5.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—5.3 GB 7.2 GB
Tight Get file →

What GPU do you need for sft v1 q4km?

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 the main file (5.3 GB file, about 7.2 GB in use).

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters7.46B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byHa-Te-21
FamilySft
Downloads (HF)300
Last updated2026-10-31

Frequently asked questions about sft v1 q4km

How much VRAM does sft v1 q4km need?

About 7.2 GB at its main file with an 8K context window. That is the 5.3 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 sft v1 q4km on an 8 GB GPU?

Yes, with the smaller files: the 5.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of sft v1 q4km GGUF?

It depends on the quant: file is 5.3 GB.

What context length does sft v1 q4km support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download sft v1 q4km GGUF?

The files are on Hugging Face in the Ha-Te-21/sft_v1_q4km repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More Sft models

All Sft →

Other small models

All small models →