TH

Theia 21B v2 Q4 K M

TheiaGGUF by aashish1904Updated 2024-09-14
Download on Hugging Face
Parameters20.4B
Context1000K
Layers70
Architecturellama
Smallest quant12.4 GB
Quick answer

Theia 21B v2 Q4 K M needs about 15.2 GB of memory at Q4_K_M (a 12.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.

Theia 21B v2 Q4 K M is a 20.4B-parameter Theia model in GGUF format, quantized by aashish1904. Its trained context length is 1000K tokens. The repository has 1 quant file, from 12.4 GB (Q4_K_M) to 12.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M12.4 GB 15.2 GB
Too big Get file →

What GPU do you need for Theia 21B v2 Q4 K M?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q4_K_M (12.4 GB file, about 15.2 GB in use).

Which Theia 21B v2 Q4 K M quant should you choose?

Q4_K_M is the usual starting point for Theia 21B v2 Q4 K M: it balances file size and quality well. Here it is a 12.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters20.4B
Layers70
Trained context1,024,000 tokens
KV cache (fp16)280 KB per token

Source

Quantized byaashish1904
FamilyTheia
Licenseother
Downloads (HF)23
Last updated2024-09-14

Frequently asked questions about Theia 21B v2 Q4 K M

How much VRAM does Theia 21B v2 Q4 K M need?

About 15.2 GB at Q4_K_M with an 8K context window. That is the 12.4 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 Theia 21B v2 Q4 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Theia 21B v2 Q4 K M GGUF?

It depends on the quant: Q4_K_M is 12.4 GB.

What context length does Theia 21B v2 Q4 K M support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.4 GB at 32K.

Where can I download Theia 21B v2 Q4 K M GGUF?

The files are on Hugging Face in the aashish1904/Theia-21B-v2-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.

What license does Theia 21B v2 Q4 K M use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Theia-21B-v2

Similar models

Browse all →

More from aashish1904

All by aashish1904 →

More Theia models

All Theia →

Other medium models

All medium models →