WE

Weyaxi Nous Hermes 2 SUS Chat 2x34B

WeyaxiGGUF by RichardErkhovUpdated 2024-08-31
Download on Hugging Face
Parameters60B
Context4K
Layers60
Architecturellama
Smallest quant9.6 GB
Quick answer

Weyaxi Nous Hermes 2 SUS Chat 2x34B needs about 39.2 GB of memory at Q4_K_M (a 36.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 22 quants, from 9.6 GB (Q5_K_M) to 64.6 GB (Q8_0).

Weyaxi Nous Hermes 2 SUS Chat 2x34B is a 60B-parameter Weyaxi model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 22 quant files, from 9.6 GB (Q5_K_M) to 64.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M9.6 GB 11.1 GB
Too big Get file →
Q3_K14.6 GB 16.1 GB
Too big Get file →
IQ3_M18.0 GB 19.5 GB
Too big Get file →
Q2_K22.4 GB 23.9 GB
Too big Get file →
IQ3_XS25.0 GB 26.5 GB
Too big Get file →
Q3_K_S26.3 GB 27.8 GB
Too big Get file →
IQ3_S26.4 GB 27.9 GB
Too big Get file →
Q3_K_M29.2 GB 30.7 GB
Too big Get file →
Q3_K_L31.8 GB 33.3 GB
Too big Get file →
IQ4_XS32.8 GB 34.3 GB
Too big Get file →
Q4_034.3 GB 35.8 GB
Too big Get file →
Q4_K_S34.6 GB 36.1 GB
Too big Get file →
IQ4_NL34.6 GB 36.2 GB
Too big Get file →
Q4_K36.7 GB 38.2 GB
Too big Get file →
Q4_K_M36.7 GB 38.2 GB
Too big Get file →
Q4_138.1 GB 39.6 GB
Too big Get file →
Q5_041.9 GB (2 parts) 43.4 GB
Too big Get file →
Q5_K_S41.9 GB (2 parts) 43.4 GB
Too big Get file →
Q5_K43.1 GB (2 parts) 44.6 GB
Too big Get file →
Q5_145.6 GB (2 parts) 47.2 GB
Too big Get file →
Q6_K49.9 GB (2 parts) 51.4 GB
Too big Get file →
Q8_064.6 GB (2 parts) 66.1 GB
Too big Get file →

What GPU do you need for Weyaxi Nous Hermes 2 SUS Chat 2x34B?

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: the best quant that fits is Q5_K_M (9.6 GB file, about 12.1 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ3_M (18.0 GB file, about 20.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q3_K_M (29.2 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K (43.1 GB file, about 45.6 GB in use).

Which Weyaxi Nous Hermes 2 SUS Chat 2x34B quant should you choose?

Q4_K_M is the usual starting point for Weyaxi Nous Hermes 2 SUS Chat 2x34B: it balances file size and quality well. Here it is a 36.7 GB file.

The Q8_0 file is 64.6 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 Q5_K_M at 9.6 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters60B (approximate, mixture of experts)
Layers60
Trained context4,096 tokens
KV cache (fp16)240 KB per token

Source

Quantized byRichardErkhov
FamilyWeyaxi
Licenseother
Downloads (HF)162
Last updated2024-08-31

Frequently asked questions about Weyaxi Nous Hermes 2 SUS Chat 2x34B

How much VRAM does Weyaxi Nous Hermes 2 SUS Chat 2x34B need?

About 39.2 GB at Q4_K_M with an 8K context window. That is the 36.7 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 Nous Hermes 2 SUS Chat 2x34B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Weyaxi Nous Hermes 2 SUS Chat 2x34B GGUF?

It depends on the quant: Q5_K_M is 9.6 GB, Q3_K is 14.6 GB, IQ3_M is 18.0 GB, Q2_K is 22.4 GB, IQ3_XS is 25.0 GB, Q3_K_S is 26.3 GB and 16 more.

What context length does Weyaxi Nous Hermes 2 SUS Chat 2x34B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.0 GB at 8K and 1.0 GB at 4K.

Where can I download Weyaxi Nous Hermes 2 SUS Chat 2x34B GGUF?

The files are on Hugging Face in the RichardErkhov/Weyaxi_-_Nous-Hermes-2-SUS-Chat-2x34B-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 Nous Hermes 2 SUS Chat 2x34B 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 →