SA

Samarkand 253m

SamarkandGGUF by Meridian-MRMUpdated 2026-10-27
Download on Hugging Face
Parameters254M
Context2K
Layers26
Architectureqwen3
Smallest quant0.1 GB
Quick answer

Samarkand 253m needs about 0.9 GB of memory at Q8_0 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB (Q2_K) to 0.5 GB (F16).

Samarkand 253m is a 254M-parameter Samarkand model in GGUF format, quantized by Meridian-MRM. Its trained context length is 2K tokens. The repository has 3 quant files, from 0.1 GB (Q2_K) to 0.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.7 GB
Fits Get file →
Q8_00.3 GB 0.8 GB
Fits Get file →
F160.5 GB 1.0 GB
Fits Get file →

What GPU do you need for Samarkand 253m?

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 F16 (0.5 GB file, about 1.1 GB in use).

Which Samarkand 253m quant should you choose?

Q8_0 (0.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q2_K at 0.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters254M
Layers26
Trained context2,048 tokens
KV cache (fp16)13 KB per token

Source

Quantized byMeridian-MRM
FamilySamarkand
Licenseapache-2.0
Downloads (HF)452
Last updated2026-10-27

Frequently asked questions about Samarkand 253m

How much VRAM does Samarkand 253m need?

About 0.9 GB at Q8_0 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 Samarkand 253m on an 8 GB GPU?

Yes, with F16: the 0.5 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Samarkand 253m GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q8_0 is 0.3 GB, F16 is 0.5 GB.

What context length does Samarkand 253m support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 2K.

Where can I download Samarkand 253m GGUF?

The files are on Hugging Face in the Meridian-MRM/Samarkand-253m repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Samarkand 253m use?

Hugging Face lists the license as apache-2.0. 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 Meridian-MRM

All by Meridian-MRM →

Other tiny models

All tiny models →