How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf theAdhiscio/Krishi-Saarthi-Gemma3nE2B:Q4_K_M# Run inference directly in the terminal:
llama cli -hf theAdhiscio/Krishi-Saarthi-Gemma3nE2B:Q4_K_MUse pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf theAdhiscio/Krishi-Saarthi-Gemma3nE2B:Q4_K_M# Run inference directly in the terminal:
./llama-cli -hf theAdhiscio/Krishi-Saarthi-Gemma3nE2B:Q4_K_MBuild from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf theAdhiscio/Krishi-Saarthi-Gemma3nE2B:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama-cli -hf theAdhiscio/Krishi-Saarthi-Gemma3nE2B:Q4_K_MUse Docker
docker model run hf.co/theAdhiscio/Krishi-Saarthi-Gemma3nE2B:Q4_K_MQuick Links
Krishi Saarthi offline-first, multimodal AI agricultural advisor built on Gemma 3n-E2B, designed to democratize expert agricultural knowledge for millions of Indian farmers in areas with low connectivity. Fine-tuning on government agricultural helpline records, Agri Saathi delivers instant, accurate farming advice in local languages, working entirely offline on mobile devices.
Based on Gemma 3n
Used Unsloth to finetune
Finetune Database: https://kcc-chakshu.icar-web.com/6_data_extract.php
- Downloads last month
- 13
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 1 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf theAdhiscio/Krishi-Saarthi-Gemma3nE2B:Q4_K_M# Run inference directly in the terminal: llama cli -hf theAdhiscio/Krishi-Saarthi-Gemma3nE2B:Q4_K_M