AS

mm4.more.star.gguf

AsciiGGUF by liminerityUpdated 2024-05-19
Download on Hugging Face
Parameters3.01B
Context32K
Layers40
Architecturellama
Smallest quant6.0 GB
Quick answer

mm4.more.star.gguf needs about 9.5 GB of memory at F16 (a 6.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 12.1 GB.

mm4.more.star.gguf is a 3.01B-parameter Ascii model in GGUF format, quantized by liminerity. Its trained context length is 32K tokens. The repository has 1 quant file, from 6.0 GB (F16) to 6.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F166.0 GB 9.5 GB
Too big Get file →

What GPU do you need for mm4.more.star.gguf?

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: the best quant that fits is F16 (6.0 GB file, about 9.5 GB in use).

Which mm4.more.star.gguf quant should you choose?

F16 (6.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.01B
Layers40
Trained context32,768 tokens
KV cache (fp16)360 KB per token

Source

Quantized byliminerity
FamilyAscii
Licenseapache-2.0
Downloads (HF)10
Last updated2024-05-19

Frequently asked questions about mm4.more.star.gguf

How much VRAM does mm4.more.star.gguf need?

About 9.5 GB at F16 with an 8K context window. That is the 6.0 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 mm4.more.star.gguf on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mm4.more.star.gguf GGUF?

It depends on the quant: F16 is 6.0 GB.

What context length does mm4.more.star.gguf support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 3.0 GB at 8K and 12.1 GB at 32K.

Where can I download mm4.more.star.gguf GGUF?

The files are on Hugging Face in the liminerity/mm4.more.star.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 mm4.more.star.gguf use?

Hugging Face lists the license as apache-2.0. 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 liminerity

All by liminerity →

More Ascii models

All Ascii →

Other tiny models

All tiny models →