OR

Oryza Sirocco 3B

OryzaGGUF by DrRiceIO7Updated 2025-12-25
Download on Hugging Face
Parameters3.43B
Context256K
Layers26
Architecturellama
Smallest quant2.1 GB
Quick answer

Oryza Sirocco 3B needs about 3.5 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.

Oryza Sirocco 3B is a 3.43B-parameter Oryza model in GGUF format, quantized by DrRiceIO7. Its trained context length is 256K tokens. The repository has 1 quant file, from 2.1 GB (Q4_K_M) to 2.1 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.1 GB 3.5 GB
Fits Get file →

What GPU do you need for Oryza Sirocco 3B?

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 Q4_K_M (2.1 GB file, about 3.5 GB in use).

Which Oryza Sirocco 3B quant should you choose?

Q4_K_M is the usual starting point for Oryza Sirocco 3B: it balances file size and quality well. Here it is a 2.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.43B
Layers26
Trained context262,144 tokens
KV cache (fp16)104 KB per token

Source

Quantized byDrRiceIO7
FamilyOryza
Downloads (HF)50
Last updated2025-12-25

Frequently asked questions about Oryza Sirocco 3B

How much VRAM does Oryza Sirocco 3B need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.1 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 Oryza Sirocco 3B on an 8 GB GPU?

Yes, with Q4_K_M: the 2.1 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Oryza Sirocco 3B GGUF?

It depends on the quant: Q4_K_M is 2.1 GB.

What context length does Oryza Sirocco 3B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.5 GB at 32K.

Where can I download Oryza Sirocco 3B GGUF?

The files are on Hugging Face in the DrRiceIO7/Oryza-Sirocco-3B-Q4_K_M-GGUF 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 Oryza models

All Oryza →

Other tiny models

All tiny models →