AU

aurelian alpha0.1 70b rope8 32K

AurelianGGUF by NoedaUpdated 2023-12-11
Download on Hugging Face
Parameters69B
Context4K
Layers80
Architecturellama
Smallest quant41.4 GB
Quick answer

aurelian alpha0.1 70b rope8 32K needs about 44.6 GB of memory at Q4_K_M (a 41.4 GB file) with an 8K context window, so it fits on a 48 GB GPU.

aurelian alpha0.1 70b rope8 32K is a 69B-parameter Aurelian model in GGUF format, quantized by Noeda. Its trained context length is 4K tokens. The repository has 1 quant file, from 41.4 GB (Q4_K_M) to 41.4 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M41.4 GB 43.3 GB
Too big Get file →

What GPU do you need for aurelian alpha0.1 70b rope8 32K?

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q4_K_M (41.4 GB file, about 44.6 GB in use).

Which aurelian alpha0.1 70b rope8 32K quant should you choose?

Q4_K_M is the usual starting point for aurelian alpha0.1 70b rope8 32K: it balances file size and quality well. Here it is a 41.4 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters69B
Layers80
Trained context4,096 tokens
KV cache (fp16)320 KB per token

Source

Quantized byNoeda
FamilyAurelian
Licensellama2
Downloads (HF)7
Last updated2023-12-11

Frequently asked questions about aurelian alpha0.1 70b rope8 32K

How much VRAM does aurelian alpha0.1 70b rope8 32K need?

About 44.6 GB at Q4_K_M with an 8K context window. That is the 41.4 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 aurelian alpha0.1 70b rope8 32K on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 44.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of aurelian alpha0.1 70b rope8 32K GGUF?

It depends on the quant: Q4_K_M is 41.4 GB.

What context length does aurelian alpha0.1 70b rope8 32K 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 aurelian alpha0.1 70b rope8 32K GGUF?

The files are on Hugging Face in the Noeda/aurelian-alpha0.1-70b-rope8-32K-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 aurelian alpha0.1 70b rope8 32K use?

Hugging Face lists the license as llama2. 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 Aurelian models

All Aurelian →

Other large models

All large models →