MCSAI - Llama Server
Ready
Conversation
Chat with llama-server models in real time
New Chat
Export
Message
Stream
Auto scroll
Idle
Stop
Send
Inspect
No request queued.
Thought Monitor
Thought Monitor
Live reasoning stream
Thought tokens will appear here when supported by the model.
Session Settings
Session Settings
Base URL
API Key
Stored only for this browser session and cleared when the tab closes.
Model
llama3.1-8b-instruct
llama3.1-70b-instruct
llama3-8b-instruct
llama3-70b-instruct
meta-llama/Llama-3.1-8B-Instruct
meta-llama/Llama-3.1-70B-Instruct
gpt-4o-mini
gpt-4.1-mini
deepseek-reasoner
Custom
Temperature
0.7
Top P
1
Presence Penalty
Frequency Penalty
Top K
Max Tokens
Response Format
Text
JSON object
System Prompt
Save
Reset Defaults
Usage Analytics
Usage Analytics
Token estimates per response
No completions yet.
Session Settings
Conversation Log
Download
Import