FI

Fimbulvetr-11B-v2.1-16K

FimbulvetrGGUF by NikolayKozloffUpdated 2024-06-30
Download on Hugging Face
Parameters10.7B
Context16K
Layers48
Architecturellama
Smallest quant11.4 GB
Quick answer

Fimbulvetr-11B-v2.1-16K needs about 13.5 GB of memory at Q8_0 (a 11.4 GB file) with an 8K context window, so it fits on a 16 GB GPU.

Fimbulvetr-11B-v2.1-16K is a 10.7B-parameter Fimbulvetr model in GGUF format, quantized by NikolayKozloff. Its trained context length is 16K tokens. The repository has 1 quant file, from 11.4 GB (Q8_0) to 11.4 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_011.4 GB 13.5 GB
Too big Get file →

What GPU do you need for Fimbulvetr-11B-v2.1-16K?

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 Q8_0 (11.4 GB file, about 13.5 GB in use).

Which Fimbulvetr-11B-v2.1-16K quant should you choose?

Q8_0 (11.4 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
Parameters10.7B
Layers48
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized byNikolayKozloff
Downloads (HF)40
Last updated2024-06-30

Frequently asked questions about Fimbulvetr-11B-v2.1-16K

How much VRAM does Fimbulvetr-11B-v2.1-16K need?

About 13.5 GB at Q8_0 with an 8K context window. That is the 11.4 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 Fimbulvetr-11B-v2.1-16K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Fimbulvetr-11B-v2.1-16K GGUF?

It depends on the quant: Q8_0 is 11.4 GB.

What context length does Fimbulvetr-11B-v2.1-16K support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download Fimbulvetr-11B-v2.1-16K GGUF?

The files are on Hugging Face in the NikolayKozloff/Fimbulvetr-11B-v2.1-16K-Q8_0-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 Fimbulvetr-11B-v2.1-16K 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.

Other GGUFs of Fimbulvetr-11B-v2.1-16K

Similar models

Browse all →

More from NikolayKozloff

All by NikolayKozloff →

More Fimbulvetr models

All Fimbulvetr →

Other medium models

All medium models →