AI

Airoboros 180b 2.2.1

AiroborosGGUF by RichardErkhovUpdated 2024-11-09
Download on Hugging Face
Parameters179B
Context2K
Layers80
Architecturefalcon
Smallest quant66.5 GB
Quick answer

Airoboros 180b 2.2.1 needs about 110.1 GB of memory at Q4_K_M (a 108.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 19 quants, from 66.5 GB (Q2_K) to 189.7 GB (Q8_0).

Airoboros 180b 2.2.1 is a 179B-parameter Airoboros model in GGUF format, quantized by RichardErkhov. Its trained context length is 2K tokens. The repository has 19 quant files, from 66.5 GB (Q2_K) to 189.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K66.5 GB (2 parts) 67.3 GB
Too big Get file →
Q3_K_S77.4 GB (2 parts) 78.2 GB
Too big Get file →
Q3_K85.1 GB (3 parts) 85.9 GB
Too big Get file →
Q3_K_M85.1 GB (3 parts) 85.9 GB
Too big Get file →
Q3_K_L91.6 GB (3 parts) 92.4 GB
Too big Get file →
IQ4_XS96.8 GB (3 parts) 97.6 GB
Too big Get file →
Q4_0100.9 GB (3 parts) 101.8 GB
Too big Get file →
Q4_K_S100.9 GB (3 parts) 101.8 GB
Too big Get file →
IQ4_NL102.0 GB (3 parts) 102.9 GB
Too big Get file →
Q4_K108.3 GB (3 parts) 109.1 GB
Too big Get file →
Q4_K_M108.3 GB (3 parts) 109.1 GB
Too big Get file →
Q4_1112.0 GB (3 parts) 112.9 GB
Too big Get file →
Q5_0123.1 GB (4 parts) 124.0 GB
Too big Get file →
Q5_K_S123.1 GB (4 parts) 124.0 GB
Too big Get file →
Q5_K130.3 GB (4 parts) 131.2 GB
Too big Get file →
Q5_K_M130.3 GB (4 parts) 131.2 GB
Too big Get file →
Q5_1134.2 GB (4 parts) 135.1 GB
Too big Get file →
Q6_K146.7 GB (4 parts) 147.6 GB
Too big Get file →
Q8_0189.7 GB (5 parts) 190.6 GB
Too big Get file →

What GPU do you need for Airoboros 180b 2.2.1?

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: 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: no quant fits at an 8K context.

Which Airoboros 180b 2.2.1 quant should you choose?

Q4_K_M is the usual starting point for Airoboros 180b 2.2.1: it balances file size and quality well. Here it is a 108.3 GB file.

The Q8_0 file is 189.7 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 66.5 GB, with the quality trade-offs that come with fewer bits. 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

Architecturefalcon
Parameters179B
Layers80
Trained context2,048 tokens
KV cache (fp16)160 KB per token

Source

Quantized byRichardErkhov
FamilyAiroboros
Licenseother
Downloads (HF)67
Last updated2024-11-09

Frequently asked questions about Airoboros 180b 2.2.1

How much VRAM does Airoboros 180b 2.2.1 need?

About 110.1 GB at Q4_K_M with an 8K context window. That is the 108.3 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 Airoboros 180b 2.2.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 68.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Airoboros 180b 2.2.1 GGUF?

It depends on the quant: Q2_K is 66.5 GB, Q3_K_S is 77.4 GB, Q3_K is 85.1 GB, Q3_K_M is 85.1 GB, Q3_K_L is 91.6 GB, IQ4_XS is 96.8 GB and 13 more.

What context length does Airoboros 180b 2.2.1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.3 GB at 8K and 0.3 GB at 2K.

Where can I download Airoboros 180b 2.2.1 GGUF?

The files are on Hugging Face in the RichardErkhov/jondurbin_-_airoboros-180b-2.2.1-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 Airoboros 180b 2.2.1 use?

Hugging Face lists the license as other. 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 RichardErkhov

All by RichardErkhov →

More Airoboros models

All Airoboros →

Other large models

All large models →