YI

Nous Hermes 2 Yi 34B i1

YiGGUF by mradermacherUpdated 2024-05-08
Download on Hugging Face
Parameters34.4B
Context4K
Layers60
Architecturellama
Smallest quant8.1 GB
Quick answer

Nous Hermes 2 Yi 34B i1 needs about 23.7 GB of memory at Q4_K_M (a 21.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 8.1 GB (IQ1_S) to 28.8 GB (Q6_K).

Nous Hermes 2 Yi 34B i1 – a 34.4B parameter Yi fine‑tuned model

Nous Hermes 2 Yi 34B i1 is a 34.4B parameter Llama‑style model fine‑tuned on 1,000,000 GPT‑4 generated entries and other high‑quality datasets. It supports tools and uses the ChatML prompt format for structured dialogue. The model is released under the Apache‑2.0 license.

Good at

  • Tool‑based task execution
  • ChatML structured conversations
  • Large context handling (4096 tokens)

Limits

  • No vision support
  • Requires 8‑k context for memory estimates
  • No explicit language support listed

Best for

  • Chatbot integration with tool calls
  • Automated code generation
  • Complex multi‑turn dialogue systems

Who it’s for. Developers building chat applications that need tool integration and structured prompts. Researchers wanting a large Yi‑fine‑tuned model with an open license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S8.1 GB 9.6 GB
Too big Get file →
IQ1_M8.2 GB 9.7 GB
Too big Get file →
IQ2_XXS9.9 GB 11.4 GB
Too big Get file →
IQ2_XS10.9 GB 12.4 GB
Too big Get file →
IQ2_S11.5 GB 13.0 GB
Too big Get file →
IQ2_M12.4 GB 13.9 GB
Too big Get file →
Q2_K13.4 GB 14.9 GB
Too big Get file →
IQ3_XXS13.9 GB 15.4 GB
Too big Get file →
IQ3_XS14.7 GB 16.2 GB
Too big Get file →
Q3_K_S15.5 GB 17.0 GB
Too big Get file →
IQ3_S15.6 GB 17.1 GB
Too big Get file →
IQ3_M16.1 GB 17.6 GB
Too big Get file →
Q3_K_M17.2 GB 18.7 GB
Too big Get file →
IQ4_XS18.5 GB 20.0 GB
Too big Get file →
Q3_K_L18.7 GB 20.2 GB
Too big Get file →
Q4_019.5 GB 21.0 GB
Too big Get file →
Q4_K_S20.1 GB 21.6 GB
Too big Get file →
Q4_K_M21.2 GB 22.7 GB
Too big Get file →
Q5_K_S24.2 GB 25.8 GB
Too big Get file →
Q5_K_M24.9 GB 26.4 GB
Too big Get file →
Q6_K28.8 GB 30.3 GB
Too big Get file →

For 8‑GB VRAM use IQ1_S (8.1 GB file, ~10.6 GB VRAM). For 12‑GB VRAM use IQ2_XS (10.91 GB file, ~13.4 GB VRAM). For 16‑GB VRAM use IQ3_XS (14.72 GB file, ~17.2 GB VRAM). Memory estimates are approximate.

What GPU do you need for Nous Hermes 2 Yi 34B i1?

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: the best quant that fits is IQ1_M (8.2 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (13.4 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (21.2 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (28.8 GB file, about 31.3 GB in use).

Which Nous Hermes 2 Yi 34B i1 quant should you choose?

Q4_K_M is the usual starting point for Nous Hermes 2 Yi 34B i1: it balances file size and quality well. Here it is a 21.2 GB file.

If memory is tight, the smallest file is IQ1_S at 8.1 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 bymradermacher
FamilyYi
Licenseapache-2.0
Downloads (HF)2,688
Last updated2024-05-08

Frequently asked questions about Nous Hermes 2 Yi 34B i1

How much VRAM does Nous Hermes 2 Yi 34B i1 need?

About 23.7 GB at Q4_K_M with an 8K context window. That is the 21.2 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 i1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nous Hermes 2 Yi 34B i1 GGUF?

It depends on the quant: IQ1_S is 8.1 GB, IQ1_M is 8.2 GB, IQ2_XXS is 9.9 GB, IQ2_XS is 10.9 GB, IQ2_S is 11.5 GB, IQ2_M is 12.4 GB and 15 more.

What context length does Nous Hermes 2 Yi 34B i1 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 i1 GGUF?

The files are on Hugging Face in the mradermacher/Nous-Hermes-2-Yi-34B-i1-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 i1 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 this model on 8 GB VRAM?

Yes, the IQ1_S quant requires about 10.6 GB VRAM at 8‑k context, which fits on an 8‑GB GPU with some swap.

Does this model support vision?

No, the model has no vision capabilities.

What prompt format does it use?

It uses the ChatML format, compatible with OpenAI’s chat API.

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

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Yi models

All Yi →

Other large models

All large models →