SP

spirit 0 2B

SpiritGGUF by aixkUpdated 2026-03-24
Download on Hugging Face
Parameters304M
Context128
Layers8
Architecturellama
Smallest quant0.2 GB
Quick answer

spirit 0 2B needs about 0.8 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. This repository has 2 quants, from 0.2 GB (Q4_K_M) to 0.6 GB (F16).

spirit 0 2B is a 304M-parameter Spirit model in GGUF format, quantized by aixk. Its trained context length is 128 tokens. The repository has 2 quant files, from 0.2 GB (Q4_K_M) to 0.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.2 GB 0.7 GB
Fits Get file →
F160.6 GB 1.1 GB
Fits Get file →

What GPU do you need for spirit 0 2B?

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 (0.6 GB file, about 1.2 GB in use).

Which spirit 0 2B quant should you choose?

Q4_K_M is the usual starting point for spirit 0 2B: 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
Parameters304M
Layers8
Trained context128 tokens
KV cache (fp16)12 KB per token

Source

Quantized byaixk
FamilySpirit
Downloads (HF)7
Last updated2026-03-24

Frequently asked questions about spirit 0 2B

How much VRAM does spirit 0 2B need?

About 0.8 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 spirit 0 2B on an 8 GB GPU?

Yes, with F16: the 0.6 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of spirit 0 2B GGUF?

It depends on the quant: Q4_K_M is 0.2 GB, F16 is 0.6 GB.

What context length does spirit 0 2B support?

The GGUF header lists a trained context length of 128 tokens (128). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 128.

Where can I download spirit 0 2B GGUF?

The files are on Hugging Face in the aixk/spirit-0_2B-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 aixk

All by aixk →

Other tiny models

All tiny models →