---

base_model: google/gemma-2b-it inference: false library_name: transformers license: other license_name: gemma-terms-of-use license_link: https://ai.google.dev/gemma/terms model_creator: Google model_name: gemma 2b it quantized_by: Second State Inc.

---

---

Gemma-2b-it

Original Model

google/gemma-2b-it

Run with LlamaEdge

• LlamaEdge version: v0.3.2
• Prompt template

- Prompt type: gemma-instruct

- Prompt string

<startofturn>user
    {usermessage}<endof_turn>
    <startofturn>model
    {modelmessage}<endof_turn>model

• Context size: 2048
• Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-2b-it-Q5KM.gguf llama-api-server.wasm -p gemma-instruct -c 4096

• Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:gemma-2b-it-Q5KM.gguf llama-chat.wasm -p gemma-instruct -c 4096

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
gemma-2b-it-Q2K.gguf	Q2K	2	900 MB	smallest, significant quality loss - not recommended for most purposes
gemma-2b-it-Q3KL.gguf	Q3K_L	3	1.26 GB	small, substantial quality loss
gemma-2b-it-Q3KM.gguf	Q3K_M	3	1.18 GB	very small, high quality loss
gemma-2b-it-Q3KS.gguf	Q3K_S	3	1.08 GB	very small, high quality loss
gemma-2b-it-Q40.gguf	Q40	4	1.42 GB	legacy; small, very high quality loss - prefer using Q3KM
gemma-2b-it-Q4KM.gguf	Q4K_M	4	1.5 GB	medium, balanced quality - recommended
gemma-2b-it-Q4KS.gguf	Q4K_S	4	1.42 GB	small, greater quality loss
gemma-2b-it-Q50.gguf	Q50	5	1.73 GB	legacy; medium, balanced quality - prefer using Q4KM
gemma-2b-it-Q5KM.gguf	Q5K_M	5	1.77 GB	large, very low quality loss - recommended
gemma-2b-it-Q5KS.gguf	Q5K_S	5	1.73 GB	large, low quality loss - recommended
gemma-2b-it-Q6K.gguf	Q6K	6	2.06 GB	very large, extremely low quality loss
gemma-2b-it-Q80.gguf	Q80	8	2.67 GB	very large, extremely low quality loss - not recommended

Quantized with llama.cpp b2230