AI

airoboros 34b 3.2

AiroborosGGUF by macadelicccUpdated 2024-03-27
Download on Hugging Face
Parameters34.4B
Context195K
Layers60
Architecturellama
Smallest quant9.3 GB
Quick answer

airoboros 34b 3.2 needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 9.3 GB (IQ2_XXS) to 28.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

airoboros 34b 3.2 is a 34.4B-parameter Airoboros model in GGUF format, quantized by macadeliccc. Its trained context length is 195K tokens. The repository has 8 quant files, from 9.3 GB (IQ2_XXS) to 28.2 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS9.3 GB 11.8 GB
Too big Get file →
IQ2_XS10.3 GB 12.8 GB
Too big Get file →
Q2_K12.8 GB 15.3 GB
Too big Get file →
Q3_K_M16.7 GB 19.2 GB
Too big Get file →
Q4_K_M20.7 GB 23.2 GB
Too big Get file →
Q5_023.7 GB 26.2 GB
Too big Get file →
Q5_K_M24.3 GB 26.8 GB
Too big Get file →
Q6_K28.2 GB 30.7 GB
Too big Get file →

What GPU do you need for airoboros 34b 3.2?

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: the best quant that fits is IQ2_XXS (9.3 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (12.8 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).

Which airoboros 34b 3.2 quant should you choose?

Q4_K_M is the usual starting point for airoboros 34b 3.2: it balances file size and quality well. Here it is a 20.7 GB file.

If memory is tight, the smallest file is IQ2_XXS at 9.3 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

Architecturellama
Parameters34.4B
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized bymacadeliccc
FamilyAiroboros
Licenseapache-2.0
Downloads (HF)173
Last updated2024-03-27

Frequently asked questions about airoboros 34b 3.2

How much VRAM does airoboros 34b 3.2 need?

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 airoboros 34b 3.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of airoboros 34b 3.2 GGUF?

It depends on the quant: IQ2_XXS is 9.3 GB, IQ2_XS is 10.3 GB, Q2_K is 12.8 GB, Q3_K_M is 16.7 GB, Q4_K_M is 20.7 GB, Q5_0 is 23.7 GB and 2 more.

What context length does airoboros 34b 3.2 support?

The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download airoboros 34b 3.2 GGUF?

The files are on Hugging Face in the macadeliccc/airoboros-34b-3.2-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 airoboros 34b 3.2 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.

Other GGUFs of airoboros-34b-3.2

Similar models

Browse all →

More from macadeliccc

All by macadeliccc →

More Airoboros models

All Airoboros →

Other large models

All large models →