WI

winta V2

WintaGGUF by kirubelmidruUpdated 2026-02-23
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant2.0 GB
Quick answer

winta V2 needs about 3.5 GB of memory at Q4_K_M (a 2.0 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 3.8 GB.

winta V2 is a 3.21B-parameter Winta model in GGUF format, quantized by kirubelmidru. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.0 GB (Q4_K_M) to 2.0 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.0 GB 3.5 GB
Fits Get file →

What GPU do you need for winta V2?

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 (2.0 GB file, about 3.5 GB in use).

Which winta V2 quant should you choose?

Q4_K_M is the usual starting point for winta V2: it balances file size and quality well. Here it is a 2.0 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bykirubelmidru
FamilyWinta
Downloads (HF)10
Last updated2026-02-23

Frequently asked questions about winta V2

How much VRAM does winta V2 need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 winta V2 on an 8 GB GPU?

Yes, with Q4_K_M: the 2.0 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 winta V2 GGUF?

It depends on the quant: Q4_K_M is 2.0 GB.

What context length does winta V2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download winta V2 GGUF?

The files are on Hugging Face in the kirubelmidru/winta_V2 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 kirubelmidru

All by kirubelmidru →

More Winta models

All Winta →

Other tiny models

All tiny models →