KA

ao karasu 72B

KarasuGGUF by mradermacherUpdated 2024-12-03
Download on Hugging Face
Parameters72.3B
Context32K
Layers80
Architectureqwen2
Smallest quant28.5 GB
Quick answer

ao karasu 72B needs about 66.1 GB of memory at Q4_K_M (a 44.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 28.5 GB (Q2_K) to 49.9 GB (Q5_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.

ao karasu 72B is a 72.3B-parameter Karasu model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 8 quant files, from 28.5 GB (Q2_K) to 49.9 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K28.5 GB 50.4 GB
Too big Get file →
Q3_K_S32.9 GB 54.9 GB
Too big Get file →
Q3_K_M35.9 GB 57.9 GB
Too big Get file →
Q3_K_L38.5 GB 60.5 GB
Too big Get file →
IQ4_XS39.1 GB 61.1 GB
Too big Get file →
Q4_K_S41.9 GB 63.9 GB
Too big Get file →
Q4_K_M44.1 GB 66.1 GB
Too big Get file →
Q5_K_S49.9 GB 71.9 GB
Too big Get file →

What GPU do you need for ao karasu 72B?

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 ao karasu 72B quant should you choose?

Q4_K_M is the usual starting point for ao karasu 72B: it balances file size and quality well. Here it is a 44.1 GB file.

If memory is tight, the smallest file is Q2_K at 28.5 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

Architectureqwen2
Parameters72.3B
Layers80
Trained context32,768 tokens
KV cache (fp16)2560 KB per token

Source

Quantized bymradermacher
FamilyKarasu
Downloads (HF)104
Last updated2024-12-03

Frequently asked questions about ao karasu 72B

How much VRAM does ao karasu 72B need?

About 66.1 GB at Q4_K_M with an 8K context window. That is the 44.1 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 ao karasu 72B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 50.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ao karasu 72B GGUF?

It depends on the quant: Q2_K is 28.5 GB, Q3_K_S is 32.9 GB, Q3_K_M is 35.9 GB, Q3_K_L is 38.5 GB, IQ4_XS is 39.1 GB, Q4_K_S is 41.9 GB and 2 more.

What context length does ao karasu 72B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 21.5 GB at 8K and 85.9 GB at 32K.

Where can I download ao karasu 72B GGUF?

The files are on Hugging Face in the mradermacher/ao-karasu-72B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of ao-karasu-72B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Karasu models

All Karasu →

Other large models

All large models →