KE

kekmodel StopCarbon 10.7B v2

KekmodelGGUF by RichardErkhovUpdated 2024-07-22
Download on Hugging Face
Parameters10.7B
Context4K
Layers—
Architecturellama
Smallest quant1.9 GB
Quick answer

kekmodel StopCarbon 10.7B v2 needs about 5.5 GB of memory at IQ3_XS (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 1.9 GB (IQ3_S) to 4.8 GB (IQ3_M).

kekmodel StopCarbon 10.7B v2 is a 10.7B-parameter Kekmodel model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 5 quant files, from 1.9 GB (IQ3_S) to 4.8 GB (IQ3_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S1.9 GB 2.5 GB
Fits Get file →
Q2_K4.0 GB 4.7 GB
Fits Get file →
IQ3_XS4.4 GB 5.2 GB
Fits Get file →
Q3_K_S4.7 GB 5.4 GB
Fits Get file →
IQ3_M4.8 GB 5.6 GB
Fits Get file →

What GPU do you need for kekmodel StopCarbon 10.7B v2?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is IQ3_S (1.9 GB file, about 2.6 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_M (4.8 GB file, about 5.9 GB in use).

Which kekmodel StopCarbon 10.7B v2 quant should you choose?

IQ3_XS (4.4 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.

If memory is tight, the smallest file is IQ3_S at 1.9 GB, with the quality trade-offs that come with fewer bits. 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
Parameters10.7B
Trained context4,096 tokens

Source

Quantized byRichardErkhov
FamilyKekmodel
Downloads (HF)19
Last updated2024-07-22

Frequently asked questions about kekmodel StopCarbon 10.7B v2

How much VRAM does kekmodel StopCarbon 10.7B v2 need?

About 5.5 GB at IQ3_XS with an 8K context window. That is the 4.4 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 kekmodel StopCarbon 10.7B v2 on an 8 GB GPU?

Yes, with IQ3_M: the 4.8 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of kekmodel StopCarbon 10.7B v2 GGUF?

It depends on the quant: IQ3_S is 1.9 GB, Q2_K is 4.0 GB, IQ3_XS is 4.4 GB, Q3_K_S is 4.7 GB, IQ3_M is 4.8 GB.

What context length does kekmodel StopCarbon 10.7B v2 support?

The GGUF header lists a trained context length of 4,096 tokens (4K).

Where can I download kekmodel StopCarbon 10.7B v2 GGUF?

The files are on Hugging Face in the RichardErkhov/kekmodel_-_StopCarbon-10.7B-v2-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Kekmodel models

All Kekmodel →

Other medium models

All medium models →