Instructions to use elizaos/eliza-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use elizaos/eliza-1 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf elizaos/eliza-1:Q4_K_M # Run inference directly in the terminal: llama cli -hf elizaos/eliza-1:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf elizaos/eliza-1:Q4_K_M # Run inference directly in the terminal: llama cli -hf elizaos/eliza-1:Q4_K_M
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 elizaos/eliza-1:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf elizaos/eliza-1:Q4_K_M
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 elizaos/eliza-1:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf elizaos/eliza-1:Q4_K_M
Use Docker
docker model run hf.co/elizaos/eliza-1:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use elizaos/eliza-1 with Ollama:
ollama run hf.co/elizaos/eliza-1:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use elizaos/eliza-1 with Docker Model Runner:
docker model run hf.co/elizaos/eliza-1:Q4_K_M
- Lemonade
How to use elizaos/eliza-1 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull elizaos/eliza-1:Q4_K_M
Run and chat with the model
lemonade run user.eliza-1-Q4_K_M
List all available models
lemonade list
- Atomic Chat
| { | |
| "files": [ | |
| { | |
| "path": "bundles/0_8b/dflash/drafter-0_8b.gguf", | |
| "sha256": "9764723c6ab89eb6c3482e14bb8ce68fd899bf724d707064c7375d02801442cb", | |
| "sizeBytes": 237637024 | |
| }, | |
| { | |
| "path": "bundles/0_8b/dflash/target-meta.json", | |
| "sha256": "580d1666b588bc9af2b7d45b7f8eed7af381b00ddb6a118b9eda9ce3801501e9", | |
| "sizeBytes": 4104 | |
| }, | |
| { | |
| "path": "bundles/0_8b/dflash/distill-manifest.json", | |
| "sha256": "86bc5b73c9d3a969eb4c8fedea6b8ff26122e745fbdcda082150f1e23f163c54", | |
| "sizeBytes": 20471 | |
| }, | |
| { | |
| "path": "bundles/0_8b/dflash/validation-structural.json", | |
| "sha256": "ba0372badf023572cf99d97db0d5d254fdce7585e83c230d7a7478f76df11774", | |
| "sizeBytes": 5155 | |
| }, | |
| { | |
| "path": "bundles/2b/dflash/drafter-2b.gguf", | |
| "sha256": "a7fcb5b35e43cf09d6e408d16a6c5261cec75cc38c1951ba96e36d2aa7425633", | |
| "sizeBytes": 679630464 | |
| }, | |
| { | |
| "path": "bundles/2b/dflash/target-meta.json", | |
| "sha256": "ca31586e43de4ac1172da677631ff2009d69cf063c30be5bda427e158e39a4af", | |
| "sizeBytes": 4100 | |
| }, | |
| { | |
| "path": "bundles/2b/dflash/distill-manifest.json", | |
| "sha256": "728c9010ef7d6d39d4adb2cc4dc066c49aaf79924196200c9833326fdaf7cf7c", | |
| "sizeBytes": 20474 | |
| }, | |
| { | |
| "path": "bundles/2b/dflash/validation-structural.json", | |
| "sha256": "c026c6fcbbd6751bc502e51fd81c91876ba4e80558c8c1c236f012be97d89abd", | |
| "sizeBytes": 5148 | |
| } | |
| ], | |
| "generatedAt": "2026-05-17T10:45:00Z", | |
| "kind": "eliza-1-dflash-h200-upload", | |
| "repositoryCommit": "dddfd1493d7dff66c69f907f317e9e99e502e481", | |
| "schemaVersion": 1 | |
| } | |