FA

Faradaylab ARIA 70B V3

FaradaylabGGUF by RichardErkhovUpdated 2024-09-02
Download on Hugging Face
Parameters69B
Context4K
Layers—
Architecturellama
Smallest quant12.1 GB
Quick answer

Faradaylab ARIA 70B V3 needs about 28.5 GB of memory at Q3_K_M (a 25.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 9 quants, from 12.1 GB (Q3_K_S) to 33.3 GB (Q3_K).

Faradaylab ARIA 70B V3 is a 69B-parameter Faradaylab model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 9 quant files, from 12.1 GB (Q3_K_S) to 33.3 GB (Q3_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S12.1 GB 13.3 GB
Too big Get file →
IQ4_XS13.7 GB 15.1 GB
Too big Get file →
Q3_K_L18.0 GB 19.6 GB
Too big Get file →
Q2_K24.0 GB 25.9 GB
Too big Get file →
Q3_K_M25.0 GB 27.0 GB
Too big Get file →
IQ3_XS28.3 GB 30.5 GB
Too big Get file →
IQ3_S29.9 GB 32.2 GB
Too big Get file →
IQ3_M30.9 GB 33.3 GB
Too big Get file →
Q3_K33.3 GB 35.8 GB
Too big Get file →

What GPU do you need for Faradaylab ARIA 70B V3?

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: 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 IQ4_XS (13.7 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q3_K_L (18.0 GB file, about 20.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_M (25.0 GB file, about 28.5 GB in use).
  • 48 GB VRAM: the best quant that fits is Q3_K (33.3 GB file, about 37.8 GB in use).

Which Faradaylab ARIA 70B V3 quant should you choose?

Q3_K_M (25.0 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 Q3_K_S at 12.1 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
Parameters69B
Trained context4,096 tokens

Source

Quantized byRichardErkhov
Downloads (HF)21
Last updated2024-09-02

Frequently asked questions about Faradaylab ARIA 70B V3

How much VRAM does Faradaylab ARIA 70B V3 need?

About 28.5 GB at Q3_K_M with an 8K context window. That is the 25.0 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 Faradaylab ARIA 70B V3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Faradaylab ARIA 70B V3 GGUF?

It depends on the quant: Q3_K_S is 12.1 GB, IQ4_XS is 13.7 GB, Q3_K_L is 18.0 GB, Q2_K is 24.0 GB, Q3_K_M is 25.0 GB, IQ3_XS is 28.3 GB and 3 more.

What context length does Faradaylab ARIA 70B V3 support?

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

Where can I download Faradaylab ARIA 70B V3 GGUF?

The files are on Hugging Face in the RichardErkhov/Faradaylab_-_ARIA-70B-V3-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 →

Other large models

All large models →