Interactive Chat

System: You are a helpful AI assistant powered by LlamaPHP.
Ready

Text Generation

0.0 0.8 2.0
0.0 0.9 1.0
Output
Output will appear here...
Ready

Real-time Streaming

Streaming shows tokens as they are generated, using the new generateStream() method.
0.0 0.7 2.0
Stream Output 0 tokens
Ready to stream

Text Embeddings

Note: Your model must support embeddings (look for models with "all-MiniLM", "bge", "e5" in name).
Embedding 1
[]
Dimension: -
Embedding 2
[]
Dimension: -
Cosine Similarity

0.00

Higher values indicate more similar meaning

Ready

Configuration & Status

Model Information
qwen3-0.6b-q4_k_m.gguf

/app/web/../models/qwen3-0.6b-q4_k_m.gguf

Size: 0.45 GB

Last modified: 2025-12-30 18:03:14

Model file found and accessible.
Llama.cpp Binary
llama-cli

/usr/local/bin/llama-cli

Executable: Yes

Permissions: 0755

Binary found and executable.
API Testing

Test the API endpoints directly:

Test API Connection Test Chat Endpoint Test Generate Endpoint