YI

Nous Hermes 2 Yi 34B IQ3 imatrix

YiGGUF by patf82Updated 2024-02-25
Download on Hugging Face
Parameters34.4B
Context4K
Layers60
Architecturellama
Smallest quant15.0 GB
Quick answer

Nous Hermes 2 Yi 34B IQ3 imatrix needs about 17.5 GB of memory at IQ3_S (a 15.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 15.0 GB (IQ3_S) to 15.6 GB (IQ3_M).

Nous Hermes 2 Yi 34B IQ3 imatrix is a 34.4B-parameter Yi model in GGUF format, quantized by patf82. Its trained context length is 4K tokens. The repository has 2 quant files, from 15.0 GB (IQ3_S) to 15.6 GB (IQ3_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S15.0 GB 16.5 GB
Too big Get file →
IQ3_M15.6 GB 17.1 GB
Too big Get file →

What GPU do you need for Nous Hermes 2 Yi 34B IQ3 imatrix?

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 IQ3_M (15.6 GB file, about 18.1 GB in use).

Which Nous Hermes 2 Yi 34B IQ3 imatrix quant should you choose?

IQ3_S (15.0 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters34.4B
Layers60
Trained context4,096 tokens
KV cache (fp16)240 KB per token

Source

Quantized bypatf82
FamilyYi
Base model01-ai/Yi-34B
Downloads (HF)45
Last updated2024-02-25

Frequently asked questions about Nous Hermes 2 Yi 34B IQ3 imatrix

How much VRAM does Nous Hermes 2 Yi 34B IQ3 imatrix need?

About 17.5 GB at IQ3_S with an 8K context window. That is the 15.0 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 Nous Hermes 2 Yi 34B IQ3 imatrix on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nous Hermes 2 Yi 34B IQ3 imatrix GGUF?

It depends on the quant: IQ3_S is 15.0 GB, IQ3_M is 15.6 GB.

What context length does Nous Hermes 2 Yi 34B IQ3 imatrix 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 Nous Hermes 2 Yi 34B IQ3 imatrix GGUF?

The files are on Hugging Face in the patf82/Nous-Hermes-2-Yi-34B-IQ3-imatrix-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 Yi-34B

Similar models

Browse all →

More Yi models

All Yi →

Other large models

All large models →