---
language:
- en
license: other
datasets:
- teknium/OpenHermes-2.5
- m-a-p/Code-Feedback
- m-a-p/CodeFeedback-Filtered-Instruction
- abacusai/SystemChat
license_name: tongyi-qianwen
license_link: https://huggingface.co/Qwen/Qwen1.5-72B/blob/main/LICENSE
quantized_by: bartowski
pipeline_tag: text-generation
---

## Llamacpp Quantizations of Liberated-Qwen1.5-7B

Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2405">b2405</a> for quantization.

Original model: https://huggingface.co/abacusai/Liberated-Qwen1.5-7B

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

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Liberated-Qwen1.5-7B-Q8_0.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q8_0.gguf) | Q8_0 | 8.20GB | Extremely high quality, generally unneeded but max available quant. |
| [Liberated-Qwen1.5-7B-Q6_K.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q6_K.gguf) | Q6_K | 6.33GB | Very high quality, near perfect, *recommended*. |
| [Liberated-Qwen1.5-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q5_K_M.gguf) | Q5_K_M | 5.52GB | High quality, very usable. |
| [Liberated-Qwen1.5-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q5_K_S.gguf) | Q5_K_S | 5.39GB | High quality, very usable. |
| [Liberated-Qwen1.5-7B-Q5_0.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q5_0.gguf) | Q5_0 | 5.39GB | High quality, older format, generally not recommended. |
| [Liberated-Qwen1.5-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q4_K_M.gguf) | Q4_K_M | 4.76GB | Good quality, similar to 4.25 bpw. |
| [Liberated-Qwen1.5-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q4_K_S.gguf) | Q4_K_S | 4.54GB | Slightly lower quality with small space savings. |
| [Liberated-Qwen1.5-7B-Q4_0.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q4_0.gguf) | Q4_0 | 4.50GB | Decent quality, older format, generally not recommended. |
| [Liberated-Qwen1.5-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q3_K_L.gguf) | Q3_K_L | 4.21GB | Lower quality but usable, good for low RAM availability. |
| [Liberated-Qwen1.5-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q3_K_M.gguf) | Q3_K_M | 3.91GB | Even lower quality. |
| [Liberated-Qwen1.5-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q3_K_S.gguf) | Q3_K_S | 3.56GB | Low quality, not recommended. |
| [Liberated-Qwen1.5-7B-Q2_K.gguf](https://huggingface.co/bartowski/Liberated-Qwen1.5-7B-GGUF/blob/main/Liberated-Qwen1.5-7B-Q2_K.gguf) | Q2_K | 3.10GB | Extremely low quality, *not* recommended.

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