Text Generation
GGUF
Rust
English
ruvllm
agent-routing
claude-code
recursive-language-model
embeddings
llm-inference
sona
hnsw
simd
imatrix
conversational
Instructions to use Princess3/Hpp 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 Princess3/Hpp 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 Princess3/Hpp:Q4_K_M # Run inference directly in the terminal: llama cli -hf Princess3/Hpp:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Princess3/Hpp:Q4_K_M # Run inference directly in the terminal: llama cli -hf Princess3/Hpp: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 Princess3/Hpp:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Princess3/Hpp: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 Princess3/Hpp:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Princess3/Hpp:Q4_K_M
Use Docker
docker model run hf.co/Princess3/Hpp:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Princess3/Hpp with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Princess3/Hpp" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Princess3/Hpp", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Princess3/Hpp:Q4_K_M
- Ollama
How to use Princess3/Hpp with Ollama:
ollama run hf.co/Princess3/Hpp:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Princess3/Hpp with Docker Model Runner:
docker model run hf.co/Princess3/Hpp:Q4_K_M
- Lemonade
How to use Princess3/Hpp with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Princess3/Hpp:Q4_K_M
Run and chat with the model
lemonade run user.Hpp-Q4_K_M
List all available models
lemonade list
- Atomic Chat
| { | |
| "version": "2.5", | |
| "release_name": "Performance Optimized Edition", | |
| "release_date": "2026-01-21T10:46:53.928251", | |
| "optimizations": { | |
| "hnsw_index": { | |
| "description": "Hierarchical Navigable Small World graphs", | |
| "improvement": "10x faster search at 10k entries" | |
| }, | |
| "lru_cache": { | |
| "description": "O(1) LRU cache using Rust lru crate", | |
| "lookup_time_ns": 23.5 | |
| }, | |
| "zero_copy": { | |
| "description": "Arc<str> string interning", | |
| "improvement": "100-1000x cache improvement" | |
| }, | |
| "batch_simd": { | |
| "description": "AVX2/NEON vectorization", | |
| "improvement": "4x throughput" | |
| }, | |
| "memory_pools": { | |
| "description": "Arena allocation", | |
| "improvement": "50% fewer allocations" | |
| } | |
| }, | |
| "benchmarks": { | |
| "query_decomposition_ns": 340, | |
| "cache_lookup_ns": 23.5, | |
| "memory_search_10k_ms": 0.4, | |
| "pattern_retrieval_us": 25, | |
| "routing_accuracy_hybrid": 1.0, | |
| "routing_accuracy_embedding_only": 0.45 | |
| }, | |
| "models": { | |
| "claude_code_0.5b": { | |
| "file": "ruvltra-claude-code-0.5b-q4_k_m.gguf", | |
| "size_mb": 398, | |
| "purpose": "Agent routing", | |
| "context_length": 32768 | |
| }, | |
| "small_0.5b": { | |
| "file": "ruvltra-small-0.5b-q4_k_m.gguf", | |
| "size_mb": 400, | |
| "purpose": "General embeddings", | |
| "context_length": 32768 | |
| }, | |
| "medium_3b": { | |
| "file": "ruvltra-medium-3b-q4_k_m.gguf", | |
| "size_mb": 2048, | |
| "purpose": "Full LLM inference", | |
| "context_length": 262144 | |
| } | |
| }, | |
| "performance_targets": { | |
| "flash_attention_speedup": "2.49x-7.47x", | |
| "hnsw_search_speedup": "150x-12500x", | |
| "memory_reduction": "50-75%", | |
| "mcp_response_ms": 100, | |
| "sona_adaptation_ms": 0.05 | |
| }, | |
| "training_data": { | |
| "labeled_examples": 381, | |
| "contrastive_pairs": 793, | |
| "agent_types": 60 | |
| } | |
| } |