KA

Kavi 350M

KaviGGUF by dgflashUpdated 2026-10-27
Download on Hugging Face
Parameters336M
Context8K
Layers24
Architecturellama
Smallest quant0.2 GB
Quick answer

Kavi 350M needs about 0.9 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Kavi 350M is a 336M-parameter Kavi model in GGUF format, quantized by dgflash. Its trained context length is 8K tokens. The repository has 1 quant file, from 0.2 GB (Q4_K_M) to 0.2 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.2 GB 0.9 GB
Fits Get file →

What GPU do you need for Kavi 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 Q4_K_M (0.2 GB file, about 0.9 GB in use).

Which Kavi 350M quant should you choose?

Q4_K_M is the usual starting point for Kavi 350M: it balances file size and quality well. Here it is a 0.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters336M
Layers24
Trained context8,192 tokens
KV cache (fp16)24 KB per token

Source

Quantized bydgflash
FamilyKavi
Downloads (HF)28
Last updated2026-10-27

Frequently asked questions about Kavi 350M

How much VRAM does Kavi 350M need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.2 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 Kavi 350M on an 8 GB GPU?

Yes, with Q4_K_M: the 0.2 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Kavi 350M GGUF?

It depends on the quant: Q4_K_M is 0.2 GB.

What context length does Kavi 350M support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download Kavi 350M GGUF?

The files are on Hugging Face in the dgflash/Kavi-350M-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 from dgflash

All by dgflash →

Other tiny models

All tiny models →