LL

Bling Sheared Llama 2.7B 0.1

LlamaGGUF by AryanneUpdated 2023-10-24
Download on Hugging Face
Parameters2.7B
Context4K
Layers32
Architecturellama
Smallest quant1.5 GB
Quick answer

Bling Sheared Llama 2.7B 0.1 needs about 4.9 GB of memory at Q4_1 (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 1.5 GB (Q4_0) to 2.9 GB (Q8_0).

Bling Sheared Llama 2.7B 0.1 is a 2.7B-parameter Llama model in GGUF format, quantized by Aryanne. Its trained context length is 4K tokens. The repository has 4 quant files, from 1.5 GB (Q4_0) to 2.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_01.5 GB 3.4 GB
Fits Get file →
Q4_11.7 GB 3.5 GB
Fits Get file →
Q5_12.0 GB 3.9 GB
Fits Get file →
Q8_02.9 GB 4.7 GB
Fits Get file →

What GPU do you need for Bling Sheared Llama 2.7B 0.1?

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_1 (2.0 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (2.9 GB file, about 6.1 GB in use).

Which Bling Sheared Llama 2.7B 0.1 quant should you choose?

Q4_1 (1.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_0 at 1.5 GB, with the quality trade-offs that come with fewer bits. 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
Parameters2.7B
Layers32
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byAryanne
FamilyLlama
Licenseapache-2.0
Downloads (HF)18
Last updated2023-10-24

Frequently asked questions about Bling Sheared Llama 2.7B 0.1

How much VRAM does Bling Sheared Llama 2.7B 0.1 need?

About 4.9 GB at Q4_1 with an 8K context window. That is the 1.7 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 Bling Sheared Llama 2.7B 0.1 on an 8 GB GPU?

Yes, with Q8_0: the 2.9 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bling Sheared Llama 2.7B 0.1 GGUF?

It depends on the quant: Q4_0 is 1.5 GB, Q4_1 is 1.7 GB, Q5_1 is 2.0 GB, Q8_0 is 2.9 GB.

What context length does Bling Sheared Llama 2.7B 0.1 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.

Where can I download Bling Sheared Llama 2.7B 0.1 GGUF?

The files are on Hugging Face in the Aryanne/Bling-Sheared-Llama-2.7B-0.1-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 Bling Sheared Llama 2.7B 0.1 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.

Similar models

Browse all →

More from Aryanne

All by Aryanne →

More Llama models

All Llama →

Other tiny models

All tiny models →