WE

Weyaxi Cosmosis 3x34B

WeyaxiGGUF by RichardErkhovUpdated 2024-11-11
Download on Hugging Face
Parameters84B
Context195K
Layers60
Architecturellama
Smallest quant0.9 GB
Quick answer

Weyaxi Cosmosis 3x34B needs about 55.2 GB of memory at Q4_K_M (a 52.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 0.9 GB (Q4_0) to 52.7 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Weyaxi Cosmosis 3x34B is a 84B-parameter Weyaxi model in GGUF format, quantized by RichardErkhov. Its trained context length is 195K tokens. The repository has 11 quant files, from 0.9 GB (Q4_0) to 52.7 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.9 GB 3.4 GB
Fits Get file →
IQ4_XS5.6 GB 8.1 GB
Too big Get file →
Q4_K_S27.6 GB 30.1 GB
Too big Get file →
Q4_K31.3 GB 33.8 GB
Too big Get file →
Q2_K32.0 GB 34.5 GB
Too big Get file →
Q3_K_S37.7 GB 40.2 GB
Too big Get file →
IQ4_NL39.4 GB 41.9 GB
Too big Get file →
Q3_K41.8 GB (2 parts) 44.3 GB
Too big Get file →
Q3_K_M41.8 GB (2 parts) 44.3 GB
Too big Get file →
Q3_K_L45.4 GB (2 parts) 47.9 GB
Too big Get file →
Q4_K_M52.7 GB (2 parts) 55.2 GB
Too big Get file →

What GPU do you need for Weyaxi Cosmosis 3x34B?

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: the best quant that fits is Q4_0 (0.9 GB file, about 3.4 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_0 (0.9 GB file, about 3.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_0 (0.9 GB file, about 3.4 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ4_XS (5.6 GB file, about 8.1 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ4_XS (5.6 GB file, about 8.1 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_XS (5.6 GB file, about 8.1 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_K_S (27.6 GB file, about 30.1 GB in use).
  • 48 GB VRAM: the best quant that fits is Q3_K_L (45.4 GB file, about 47.9 GB in use).

Which Weyaxi Cosmosis 3x34B quant should you choose?

Q4_K_M is the usual starting point for Weyaxi Cosmosis 3x34B: it balances file size and quality well. Here it is a 52.7 GB file.

If memory is tight, the smallest file is Q4_0 at 0.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters84B (approximate, mixture of experts)
Layers60
Trained context200,000 tokens
KV cache (fp16)240 KB per token

Source

Quantized byRichardErkhov
FamilyWeyaxi
Licenseother
Downloads (HF)4
Last updated2024-11-11

Frequently asked questions about Weyaxi Cosmosis 3x34B

How much VRAM does Weyaxi Cosmosis 3x34B need?

About 55.2 GB at Q4_K_M with an 8K context window. That is the 52.7 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 Weyaxi Cosmosis 3x34B on an 8 GB GPU?

Yes, with Q4_0: the 0.9 GB file needs about 3.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Weyaxi Cosmosis 3x34B GGUF?

It depends on the quant: Q4_0 is 0.9 GB, IQ4_XS is 5.6 GB, Q4_K_S is 27.6 GB, Q4_K is 31.3 GB, Q2_K is 32.0 GB, Q3_K_S is 37.7 GB and 5 more.

What context length does Weyaxi Cosmosis 3x34B 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 Weyaxi Cosmosis 3x34B GGUF?

The files are on Hugging Face in the RichardErkhov/Weyaxi_-_Cosmosis-3x34B-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 Weyaxi Cosmosis 3x34B 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 Weyaxi models

All Weyaxi →

Other large models

All large models →