ST

stella-base-zh-v2

StellaGGUF by wencan-labUpdated 2024-07-24
Download on Hugging Face
Parameters102M
Context1K
Layers12
Architecturebert
Smallest quant0.1 GB
Quick answer

stella-base-zh-v2 needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.

stella-base-zh-v2 is a 102M-parameter Stella model in GGUF format, quantized by wencan-lab. Its trained context length is 1K tokens. The repository has 1 quant file, from 0.1 GB (Q4_K_M) to 0.1 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.1 GB 0.6 GB
Fits Get file →

What GPU do you need for stella-base-zh-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 (0.1 GB file, about 0.9 GB in use).

Which stella-base-zh-v2 quant should you choose?

Q4_K_M is the usual starting point for stella-base-zh-v2: it balances file size and quality well. Here it is a 0.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebert
Parameters102M
Layers12
Trained context1,024 tokens
KV cache (fp16)36 KB per token

Source

Quantized bywencan-lab
FamilyStella
Licensemit
Downloads (HF)8
Last updated2024-07-24

Frequently asked questions about stella-base-zh-v2

How much VRAM does stella-base-zh-v2 need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.1 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 stella-base-zh-v2 on an 8 GB GPU?

Yes, with Q4_K_M: the 0.1 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 stella-base-zh-v2 GGUF?

It depends on the quant: Q4_K_M is 0.1 GB.

What context length does stella-base-zh-v2 support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 1K.

Where can I download stella-base-zh-v2 GGUF?

The files are on Hugging Face in the wencan-lab/stella-base-zh-v2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does stella-base-zh-v2 use?

Hugging Face lists the license as mit. 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 wencan-lab

All by wencan-lab →

More Stella models

All Stella →

Other tiny models

All tiny models →