---
language:
- en
license: other
library_name: transformers
tags:
- code
- chemistry
- medical
datasets:
- Locutusque/hyperion-v3.0
quantized_by: bartowski
pipeline_tag: text-generation
---

## Llamacpp Quantizations of Hyperion-3.0-Yi-34B

Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2440">b2440</a> for quantization.

Original model: https://huggingface.co/Locutusque/Hyperion-3.0-Yi-34B

Download a file (not the whole branch) from below:

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Hyperion-3.0-Yi-34B-Q8_0.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q8_0.gguf) | Q8_0 | 36.54GB | Extremely high quality, generally unneeded but max available quant. |
| [Hyperion-3.0-Yi-34B-Q6_K.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q6_K.gguf) | Q6_K | 28.21GB | Very high quality, near perfect, *recommended*. |
| [Hyperion-3.0-Yi-34B-Q5_K_M.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q5_K_M.gguf) | Q5_K_M | 24.32GB | High quality, very usable. |
| [Hyperion-3.0-Yi-34B-Q5_K_S.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q5_K_S.gguf) | Q5_K_S | 23.70GB | High quality, very usable. |
| [Hyperion-3.0-Yi-34B-Q5_0.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q5_0.gguf) | Q5_0 | 23.70GB | High quality, older format, generally not recommended. |
| [Hyperion-3.0-Yi-34B-Q4_K_M.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q4_K_M.gguf) | Q4_K_M | 20.65GB | Good quality, similar to 4.25 bpw. |
| [Hyperion-3.0-Yi-34B-Q4_K_S.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q4_K_S.gguf) | Q4_K_S | 19.59GB | Slightly lower quality with small space savings. |
| [Hyperion-3.0-Yi-34B-Q4_0.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q4_0.gguf) | Q4_0 | 19.46GB | Decent quality, older format, generally not recommended. |
| [Hyperion-3.0-Yi-34B-Q3_K_L.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q3_K_L.gguf) | Q3_K_L | 18.13GB | Lower quality but usable, good for low RAM availability. |
| [Hyperion-3.0-Yi-34B-Q3_K_M.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q3_K_M.gguf) | Q3_K_M | 16.65GB | Even lower quality. |
| [Hyperion-3.0-Yi-34B-Q3_K_S.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q3_K_S.gguf) | Q3_K_S | 14.96GB | Low quality, not recommended. |
| [Hyperion-3.0-Yi-34B-Q2_K.gguf](https://huggingface.co/bartowski/Hyperion-3.0-Yi-34B-GGUF/blob/main/Hyperion-3.0-Yi-34B-Q2_K.gguf) | Q2_K | 12.82GB | Extremely low quality, *not* recommended.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski