SA

Sarashina2.1 1b

SarashinaGGUF by Mori-kamiyamaUpdated 2025-02-14
Download on Hugging Face
Parameters1.41B
Context8K
Layers24
Architecturellama
Smallest quant0.9 GB
Quick answer

Sarashina2.1 1b needs about 2.1 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.9 GB (Q4_K_M) to 1.5 GB (Q8_0).

Sarashina2.1 1b is a 1.41B-parameter Sarashina model in GGUF format, quantized by Mori-kamiyama. Its trained context length is 8K tokens. The repository has 3 quant files, from 0.9 GB (Q4_K_M) to 1.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.9 GB 2.1 GB
Fits Get file →
Q5_K_M1.1 GB 2.3 GB
Fits Get file →
Q8_01.5 GB 2.7 GB
Fits Get file →

What GPU do you need for Sarashina2.1 1b?

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 Q8_0 (1.5 GB file, about 2.7 GB in use).

Which Sarashina2.1 1b quant should you choose?

Q4_K_M is the usual starting point for Sarashina2.1 1b: it balances file size and quality well. Here it is a 0.9 GB file.

The Q8_0 file is 1.5 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

Architecturellama
Parameters1.41B
Layers24
Trained context8,192 tokens
KV cache (fp16)84 KB per token

Source

Quantized byMori-kamiyama
FamilySarashina
Downloads (HF)55
Last updated2025-02-14

Frequently asked questions about Sarashina2.1 1b

How much VRAM does Sarashina2.1 1b need?

About 2.1 GB at Q4_K_M with an 8K context window. That is the 0.9 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 Sarashina2.1 1b on an 8 GB GPU?

Yes, with Q8_0: the 1.5 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sarashina2.1 1b GGUF?

It depends on the quant: Q4_K_M is 0.9 GB, Q5_K_M is 1.1 GB, Q8_0 is 1.5 GB.

What context length does Sarashina2.1 1b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.7 GB at 8K and 0.7 GB at 8K.

Where can I download Sarashina2.1 1b GGUF?

The files are on Hugging Face in the Mori-kamiyama/sarashina2.1-1b-r1 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 from Mori-kamiyama

All by Mori-kamiyama →

More Sarashina models

All Sarashina →

Other tiny models

All tiny models →