MO

Moist Theia 21B Q8 0

MoistGGUF by SzilviaBUpdated 2024-09-29
Download on Hugging Face
Parameters20.4B
Context1000K
Layers70
Architecturellama
Smallest quant43.4 GB
Quick answer

Moist Theia 21B Q8 0 needs about 46.3 GB of memory at Q8_0 (a 43.4 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.

Moist Theia 21B Q8 0 is a 20.4B-parameter Moist model in GGUF format, quantized by SzilviaB. Its trained context length is 1000K tokens. The repository has 1 quant file, from 43.4 GB (Q8_0) to 43.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_043.4 GB (4 parts) 46.3 GB
Too big Get file →

What GPU do you need for Moist Theia 21B Q8 0?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q8_0 (43.4 GB file, about 46.3 GB in use).

Which Moist Theia 21B Q8 0 quant should you choose?

Q8_0 (43.4 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

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 bySzilviaB
FamilyMoist
Downloads (HF)41
Last updated2024-09-29

Frequently asked questions about Moist Theia 21B Q8 0

How much VRAM does Moist Theia 21B Q8 0 need?

About 46.3 GB at Q8_0 with an 8K context window. That is the 43.4 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 Moist Theia 21B Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 46.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Moist Theia 21B Q8 0 GGUF?

It depends on the quant: Q8_0 is 43.4 GB.

What context length does Moist Theia 21B Q8 0 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 Moist Theia 21B Q8 0 GGUF?

The files are on Hugging Face in the SzilviaB/Moist_Theia_21B-Q8_0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Moist_Theia_21B

Similar models

Browse all →

More from SzilviaB

All by SzilviaB →

More Moist models

All Moist →

Other medium models

All medium models →