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 iAkashPaul/gemma-2b-it-gguf:# Run inference directly in the terminal:
llama cli -hf iAkashPaul/gemma-2b-it-gguf:Use 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 iAkashPaul/gemma-2b-it-gguf:# Run inference directly in the terminal:
./llama-cli -hf iAkashPaul/gemma-2b-it-gguf:Build 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 iAkashPaul/gemma-2b-it-gguf:# Run inference directly in the terminal:
./build/bin/llama-cli -hf iAkashPaul/gemma-2b-it-gguf:Use Docker
docker model run hf.co/iAkashPaul/gemma-2b-it-gguf:Quick Links
Gemma 2B Instruct GGUF
Contains Q4 & Q8 quantized GGUFs for google/gemma
Perf
| Variant | Device | Perf |
|---|---|---|
| Q4 | M1 Pro 10-core GPU | 90 tok/s |
| Snapdragon 778G CPU | 10 tok/s | |
| RTX 2070S | 40 tok/s | |
| Q8 | M1 Pro 10-core GPU | 54 tok/s |
| Snapdragon 778G CPU | 6 tok/s | |
| RTX 2070S | 25 tok/s | |
| F16 | M1 Pro 10-core GPU | 30 tok/s |
| Snapdragon 778G CPU | <1 tok/s |
- Downloads last month
- 96
Hardware compatibility
Log In to add your hardware
4-bit
8-bit
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf iAkashPaul/gemma-2b-it-gguf:# Run inference directly in the terminal: llama cli -hf iAkashPaul/gemma-2b-it-gguf: