GL

Glitz v0.2 โœจ๐Ÿ’…

GlitzGGUF by FizzarolliUpdated 2024-08-03
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Glitz v0.2 โœจ๐Ÿ’… needs about 29.6 GB of memory at Q2_K (a 26.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 26.4 GB (Q2_K) to 141.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Glitz v0.2 โœจ๐Ÿ’… is a 70.6B-parameter Glitz model in GGUF format, quantized by Fizzarolli. Its trained context length is 128K tokens. The repository has 2 quant files, from 26.4 GB (Q2_K) to 141.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 GB
Too big Get file →
BF16141.1 GB (3 parts) 144.3 GB
Too big Get file →

What GPU do you need for Glitz v0.2 โœจ๐Ÿ’…?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).

Which Glitz v0.2 โœจ๐Ÿ’… quant should you choose?

Q2_K (26.4 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byFizzarolli
FamilyGlitz
Licensellama3.1
Downloads (HF)3
Last updated2024-08-03

Frequently asked questions about Glitz v0.2 โœจ๐Ÿ’…

How much VRAM does Glitz v0.2 โœจ๐Ÿ’… need?

About 29.6 GB at Q2_K with an 8K context window. That is the 26.4 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 Glitz v0.2 โœจ๐Ÿ’… on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Glitz v0.2 โœจ๐Ÿ’… GGUF?

It depends on the quant: Q2_K is 26.4 GB, BF16 is 141.1 GB.

What context length does Glitz v0.2 โœจ๐Ÿ’… support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Glitz v0.2 โœจ๐Ÿ’… GGUF?

The files are on Hugging Face in the Fizzarolli/L3.1-70b-glitz-v0.2-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 Glitz v0.2 โœจ๐Ÿ’… use?

Hugging Face lists the license as llama3.1. 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 Fizzarolli

All by Fizzarolli →

More Glitz models

All Glitz →

Other large models

All large models →