YI

Nous Hermes 2 Yi 34B

YiGGUF by TheBlokeUpdated 2023-12-26
Download on Hugging Face
Parameters34.4B
Context4K
Layers60
Architecturellama
Smallest quant14.6 GB
Quick answer

Nous Hermes 2 Yi 34B needs about 23.2 GB of memory at Q4_K_M (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 14.6 GB (Q2_K) to 36.5 GB (Q8_0).

34‑billion‑parameter Yi‑based LLM with tool‑use capability

Nous Hermes 2 Yi 34B is a 34 billion‑parameter model fine‑tuned on GPT‑4‑generated data and other high‑quality datasets. It supports the ChatML prompt format and is available in GGUF format for llama.cpp and compatible clients.

Good at

  • Tool‑use in multi‑turn dialogue
  • ChatML prompt compatibility
  • Large context handling

Limits

  • Requires 8 k context for full performance
  • No vision or multimodal support
  • Apache‑2.0 license restricts commercial redistribution

Best for

  • Chat‑based applications needing tool integration
  • Local LLM deployments with GPU acceleration
  • Developers testing large‑scale fine‑tunes

Who it’s for. The model is suited for developers and researchers who need a large, tool‑enabled LLM for local deployment. It is ideal for those using llama.cpp or compatible GUIs to run the model on GPU hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K14.6 GB 16.1 GB
Too big Get file →
Q3_K_S15.0 GB 16.5 GB
Too big Get file →
Q3_K_M16.6 GB 18.1 GB
Too big Get file →
Q3_K_L18.1 GB 19.6 GB
Too big Get file →
Q4_019.5 GB 21.0 GB
Too big Get file →
Q4_K_S19.5 GB 21.1 GB
Too big Get file →
Q4_K_M20.7 GB 22.2 GB
Too big Get file →
Q5_023.7 GB 25.2 GB
Too big Get file →
Q5_K_S23.7 GB 25.2 GB
Too big Get file →
Q5_K_M24.3 GB 25.8 GB
Too big Get file →
Q6_K28.2 GB 29.7 GB
Too big Get file →
Q8_036.5 GB 38.0 GB
Too big Get file →

For 8 GB VRAM, use Q4_K (19.47 GB file, ~22 GB RAM). For 12 GB VRAM, Q5_K_M (24.32 GB file, ~26.8 GB RAM). For 16 GB VRAM, Q6_K (28.21 GB file, ~30.7 GB RAM). These estimates are approximate.

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

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 Q4_K_M (20.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.2 GB file, about 30.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (36.5 GB file, about 39.1 GB in use).

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

Q4_K_M is the usual starting point for Nous Hermes 2 Yi 34B: it balances file size and quality well. Here it is a 20.7 GB file.

The Q8_0 file is 36.5 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 Q2_K at 14.6 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

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

Source

Quantized byTheBloke
FamilyYi
Licenseapache-2.0
Downloads (HF)3,596
Last updated2023-12-26

Frequently asked questions about Nous Hermes 2 Yi 34B

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

About 23.2 GB at Q4_K_M with an 8K context window. That is the 20.7 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 Nous Hermes 2 Yi 34B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.1 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q2_K is 14.6 GB, Q3_K_S is 15.0 GB, Q3_K_M is 16.6 GB, Q3_K_L is 18.1 GB, Q4_0 is 19.5 GB, Q4_K_S is 19.5 GB and 6 more.

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

The files are on Hugging Face in the TheBloke/Nous-Hermes-2-Yi-34B-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 Nous Hermes 2 Yi 34B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Nous Hermes 2 Yi 34B on 8 GB VRAM?

Use the Q4_K quantized model; it requires about 22 GB of RAM and a 19.47 GB file.

Does the model support image input?

No, the model has no vision or multimodal capabilities.

What prompt format does it use?

It uses ChatML, the same format as OpenAI’s chat API.

Other GGUFs of Nous-Hermes-2-Yi-34B

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Yi models

All Yi →

Other large models

All large models →