MO

MOE-Finetuned-4B

MoeGGUF by KlevinUpdated 2024-06-22
Download on Hugging Face
Parameters7.25B
Context32K
Layers32
Architecturellama
Smallest quant3.8 GB
Quick answer

MOE-Finetuned-4B needs about 5.4 GB of memory at Q3_K_L (a 3.8 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 4.3 GB.

MOE-Finetuned-4B is a 7.25B-parameter Moe model in GGUF format, quantized by Klevin. Its trained context length is 32K tokens. The repository has 1 quant file, from 3.8 GB (Q3_K_L) to 3.8 GB (Q3_K_L).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_L3.8 GB 5.4 GB
Fits Get file →

What GPU do you need for MOE-Finetuned-4B?

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 Q3_K_L (3.8 GB file, about 5.4 GB in use).

Which MOE-Finetuned-4B quant should you choose?

Q3_K_L (3.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.25B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byKlevin
FamilyMoe
Licenseapache-2.0
Downloads (HF)10
Last updated2024-06-22

Frequently asked questions about MOE-Finetuned-4B

How much VRAM does MOE-Finetuned-4B need?

About 5.4 GB at Q3_K_L with an 8K context window. That is the 3.8 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 MOE-Finetuned-4B on an 8 GB GPU?

Yes, with Q3_K_L: the 3.8 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MOE-Finetuned-4B GGUF?

It depends on the quant: Q3_K_L is 3.8 GB.

What context length does MOE-Finetuned-4B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download MOE-Finetuned-4B GGUF?

The files are on Hugging Face in the Klevin/MOE-Finetuned-4B-Q3_K_L-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 MOE-Finetuned-4B 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 MOE-Finetuned-4B

Similar models

Browse all →

More from Klevin

All by Klevin →

More Moe models

All Moe →

Other small models

All small models →