Gemma-2-9b-it-GGUF

Original Model

google/gemma-2-9b-it

Run with Gaianet

Prompt template:

prompt template: gemma-instruct

Context size:

  • Max

chat_ctx_size: 8192

  • Recommend

chat_ctx_size: 4096

Run with GaiaNet:

Quantized with llama.cpp b3259

Downloads last month
31
GGUF
Model size
9.24B params
Architecture
gemma2

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for gaianet/gemma-2-9b-it-GGUF

Base model

google/gemma-2-9b
Quantized
(112)
this model

Collection including gaianet/gemma-2-9b-it-GGUF