SU

Sutra Instruct 350M

SutraGGUF by AbirayUpdated 2026-03-17
Download on Hugging Face
Parameters406M
Context1K
Layers24
Architecturegpt2
Smallest quant0.3 GB
Quick answer

Sutra Instruct 350M needs about 1.6 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.3 GB (Q4_K_M) to 0.8 GB.

Sutra Instruct 350M is a 406M-parameter Sutra model in GGUF format, quantized by Abiray. Its trained context length is 1K tokens. The repository has 3 quant files, from 0.3 GB (Q4_K_M) to 0.8 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.3 GB 0.9 GB
Fits Get file →
Q8_00.4 GB 1.0 GB
Fits Get file →
—0.8 GB 1.4 GB
Fits Get file →

What GPU do you need for Sutra Instruct 350M?

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: the best quant that fits is the main file (0.8 GB file, about 2.1 GB in use).

Which Sutra Instruct 350M quant should you choose?

Q4_K_M is the usual starting point for Sutra Instruct 350M: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.4 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt2
Parameters406M
Layers24
Trained context1,024 tokens
KV cache (fp16)96 KB per token

Source

Quantized byAbiray
FamilySutra
Licensemit
Downloads (HF)127
Last updated2026-03-17

Frequently asked questions about Sutra Instruct 350M

How much VRAM does Sutra Instruct 350M need?

About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.3 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 Sutra Instruct 350M on an 8 GB GPU?

Yes, with the smaller files: the 0.8 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sutra Instruct 350M GGUF?

It depends on the quant: Q4_K_M is 0.3 GB, Q8_0 is 0.4 GB, file is 0.8 GB.

What context length does Sutra Instruct 350M support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 1K.

Where can I download Sutra Instruct 350M GGUF?

The files are on Hugging Face in the Abiray/Sutra-Instruct-350M-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 Sutra Instruct 350M 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.

Similar models

Browse all →

More from Abiray

All by Abiray →

Other tiny models

All tiny models →