AY

Aya23 35B Hok v3

AyaGGUF by mradermacherUpdated 2024-09-28
Download on Hugging Face
Parameters35B
Context8K
Layers40
Architecturecommand-r
Smallest quant8.5 GB
Quick answer

Aya23 35B Hok v3 needs about 32.8 GB of memory at Q4_K_M (a 21.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 21 quants, from 8.5 GB (IQ1_S) to 28.7 GB (Q6_K).

Aya23 35B Hok v3 is a 35B-parameter Aya model in GGUF format, quantized by mradermacher. Its trained context length is 8K tokens. The repository has 21 quant files, from 8.5 GB (IQ1_S) to 28.7 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S8.5 GB 19.8 GB
Too big Get file →
IQ1_M9.1 GB 20.4 GB
Too big Get file →
IQ2_XXS10.2 GB 21.4 GB
Too big Get file →
IQ2_XS11.1 GB 22.3 GB
Too big Get file →
IQ2_S11.8 GB 23.1 GB
Too big Get file →
IQ2_M12.7 GB 23.9 GB
Too big Get file →
Q2_K13.8 GB 25.1 GB
Too big Get file →
IQ3_XXS13.8 GB 25.1 GB
Too big Get file →
IQ3_XS15.1 GB 26.3 GB
Too big Get file →
IQ3_S15.9 GB 27.1 GB
Too big Get file →
Q3_K_S15.9 GB 27.1 GB
Too big Get file →
IQ3_M16.7 GB 27.9 GB
Too big Get file →
Q3_K_M17.6 GB 28.9 GB
Too big Get file →
Q3_K_L19.1 GB 30.4 GB
Too big Get file →
IQ4_XS19.2 GB 30.4 GB
Too big Get file →
Q4_020.3 GB 31.5 GB
Too big Get file →
Q4_K_S20.4 GB 31.6 GB
Too big Get file →
Q4_K_M21.5 GB 32.8 GB
Too big Get file →
Q5_K_S24.3 GB 35.6 GB
Too big Get file →
Q5_K_M25.0 GB 36.2 GB
Too big Get file →
Q6_K28.7 GB 39.9 GB
Too big Get file →

What GPU do you need for Aya23 35B Hok v3?

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: the best quant that fits is IQ2_M (12.7 GB file, about 23.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_S (20.4 GB file, about 31.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (28.7 GB file, about 39.9 GB in use).

Which Aya23 35B Hok v3 quant should you choose?

Q4_K_M is the usual starting point for Aya23 35B Hok v3: it balances file size and quality well. Here it is a 21.5 GB file.

If memory is tight, the smallest file is IQ1_S at 8.5 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

Architecturecommand-r
Parameters35B
Layers40
Trained context8,192 tokens
KV cache (fp16)1280 KB per token

Source

Quantized bymradermacher
FamilyAya
Downloads (HF)14
Last updated2024-09-28

Frequently asked questions about Aya23 35B Hok v3

How much VRAM does Aya23 35B Hok v3 need?

About 32.8 GB at Q4_K_M with an 8K context window. That is the 21.5 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 Aya23 35B Hok v3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Aya23 35B Hok v3 GGUF?

It depends on the quant: IQ1_S is 8.5 GB, IQ1_M is 9.1 GB, IQ2_XXS is 10.2 GB, IQ2_XS is 11.1 GB, IQ2_S is 11.8 GB, IQ2_M is 12.7 GB and 15 more.

What context length does Aya23 35B Hok v3 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 10.7 GB at 8K and 10.7 GB at 8K.

Where can I download Aya23 35B Hok v3 GGUF?

The files are on Hugging Face in the mradermacher/Aya23-35B-hok-v3-i1-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 mradermacher

All by mradermacher →

More Aya models

All Aya →

Other large models

All large models →