|
--- |
|
library_name: transformers |
|
widget: |
|
- messages: |
|
- role: user |
|
content: How does the brain work? |
|
inference: |
|
parameters: |
|
max_new_tokens: 200 |
|
extra_gated_heading: Access Gemma on Hugging Face |
|
extra_gated_prompt: >- |
|
To access Gemma on Hugging Face, you’re required to review and agree to |
|
Google’s usage license. To do this, please ensure you’re logged-in to Hugging |
|
Face and click below. Requests are processed immediately. |
|
extra_gated_button_content: Acknowledge license |
|
license: gemma |
|
quantized_by: bartowski |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
## Llamacpp Quantizations of gemma-1.1-7b-it |
|
|
|
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2589">b2589</a> for quantization. |
|
|
|
Original model: https://huggingface.co/google/gemma-1.1-7b-it |
|
|
|
Download a file (not the whole branch) from below: |
|
|
|
| Filename | Quant type | File Size | Description | |
|
| -------- | ---------- | --------- | ----------- | |
|
| [gemma-1.1-7b-it-Q8_0.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q8_0.gguf) | Q8_0 | 9.07GB | Extremely high quality, generally unneeded but max available quant. | |
|
| [gemma-1.1-7b-it-Q6_K.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q6_K.gguf) | Q6_K | 7.01GB | Very high quality, near perfect, *recommended*. | |
|
| [gemma-1.1-7b-it-Q5_K_M.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q5_K_M.gguf) | Q5_K_M | 6.14GB | High quality, very usable. | |
|
| [gemma-1.1-7b-it-Q5_K_S.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q5_K_S.gguf) | Q5_K_S | 5.98GB | High quality, very usable. | |
|
| [gemma-1.1-7b-it-Q5_0.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q5_0.gguf) | Q5_0 | 5.98GB | High quality, older format, generally not recommended. | |
|
| [gemma-1.1-7b-it-Q4_K_M.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q4_K_M.gguf) | Q4_K_M | 5.32GB | Good quality, uses about 4.83 bits per weight. | |
|
| [gemma-1.1-7b-it-Q4_K_S.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q4_K_S.gguf) | Q4_K_S | 5.04GB | Slightly lower quality with small space savings. | |
|
| [gemma-1.1-7b-it-IQ4_NL.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-IQ4_NL.gguf) | IQ4_NL | 5.04GB | Decent quality, similar to Q4_K_S, new method of quanting, | |
|
| [gemma-1.1-7b-it-IQ4_XS.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-IQ4_XS.gguf) | IQ4_XS | 4.80GB | Decent quality, new method with similar performance to Q4. | |
|
| [gemma-1.1-7b-it-Q4_0.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q4_0.gguf) | Q4_0 | 5.01GB | Decent quality, older format, generally not recommended. | |
|
| [gemma-1.1-7b-it-Q3_K_L.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q3_K_L.gguf) | Q3_K_L | 4.70GB | Lower quality but usable, good for low RAM availability. | |
|
| [gemma-1.1-7b-it-Q3_K_M.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q3_K_M.gguf) | Q3_K_M | 4.36GB | Even lower quality. | |
|
| [gemma-1.1-7b-it-IQ3_M.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-IQ3_M.gguf) | IQ3_M | 4.10GB | Medium-low quality, new method with decent performance. | |
|
| [gemma-1.1-7b-it-IQ3_S.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-IQ3_S.gguf) | IQ3_S | 3.98GB | Lower quality, new method with decent performance, recommended over Q3 quants. | |
|
| [gemma-1.1-7b-it-Q3_K_S.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q3_K_S.gguf) | Q3_K_S | 3.98GB | Low quality, not recommended. | |
|
| [gemma-1.1-7b-it-Q2_K.gguf](https://huggingface.co/bartowski/gemma-1.1-7b-it-GGUF/blob/main/gemma-1.1-7b-it-Q2_K.gguf) | Q2_K | 3.48GB | Extremely low quality, *not* recommended. | |
|
|
|
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski |
|
|
