FI

FimLotus 2x10.7B

FimlotusGGUF by gelukuMLGUpdated 2024-03-24
Download on Hugging Face
Parameters19.2B
Context4K
Layers48
Architecturellama
Smallest quant10.9 GB
Quick answer

FimLotus 2x10.7B needs about 13.0 GB of memory at Q4_K_S (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU.

FimLotus 2x10.7B is a 19.2B-parameter Fimlotus model in GGUF format, quantized by gelukuMLG. Its trained context length is 4K tokens. The repository has 1 quant file, from 10.9 GB (Q4_K_S) to 10.9 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S10.9 GB 12.2 GB
Too big Get file →

What GPU do you need for FimLotus 2x10.7B?

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_S (10.9 GB file, about 13.0 GB in use).

Which FimLotus 2x10.7B quant should you choose?

Q4_K_S (10.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters19.2B (approximate, mixture of experts)
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bygelukuMLG
FamilyFimlotus
Downloads (HF)26
Last updated2024-03-24

Frequently asked questions about FimLotus 2x10.7B

How much VRAM does FimLotus 2x10.7B need?

About 13.0 GB at Q4_K_S with an 8K context window. That is the 10.9 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 FimLotus 2x10.7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of FimLotus 2x10.7B GGUF?

It depends on the quant: Q4_K_S is 10.9 GB.

What context length does FimLotus 2x10.7B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download FimLotus 2x10.7B GGUF?

The files are on Hugging Face in the gelukuMLG/FimLotus-2x10.7B-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 FimLotus 2x10.7B use?

Hugging Face lists the license as cc-by-nc-4.0. 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 gelukuMLG

All by gelukuMLG →

Other medium models

All medium models →