ST

mm4.star Q5 K S

StarGGUF by gate369Updated 2024-03-30
Download on Hugging Face
Parameters3.01B
Context32K
Layers40
Architecturellama
Smallest quant2.1 GB
Quick answer

mm4.star Q5 K S needs about 5.7 GB of memory at Q5_K_S (a 2.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 12.1 GB.

mm4.star Q5 K S is a 3.01B-parameter Star model in GGUF format, quantized by gate369. Its trained context length is 32K tokens. The repository has 1 quant file, from 2.1 GB (Q5_K_S) to 2.1 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S2.1 GB 5.7 GB
Fits Get file →

What GPU do you need for mm4.star Q5 K S?

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: the best quant that fits is Q5_K_S (2.1 GB file, about 5.7 GB in use).

Which mm4.star Q5 K S quant should you choose?

Q5_K_S (2.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

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 bygate369
FamilyStar
Licenseapache-2.0
Downloads (HF)12
Last updated2024-03-30

Frequently asked questions about mm4.star Q5 K S

How much VRAM does mm4.star Q5 K S need?

About 5.7 GB at Q5_K_S with an 8K context window. That is the 2.1 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 mm4.star Q5 K S on an 8 GB GPU?

Yes, with Q5_K_S: the 2.1 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mm4.star Q5 K S GGUF?

It depends on the quant: Q5_K_S is 2.1 GB.

What context length does mm4.star Q5 K S 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.star Q5 K S GGUF?

The files are on Hugging Face in the gate369/mm4.star-Q5_K_S-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.star Q5 K S 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.

Other GGUFs of mm4.star

Similar models

Browse all →

More from gate369

All by gate369 →

More Star models

All Star →

Other tiny models

All tiny models →