Qwen3.5 Chat (ऑन-डिवाइस LLM)

import Qwen3Chat

let chat = try await Qwen35MLXChat.fromPretrained()

// Single response
let response = try chat.generate(messages: [
    ChatMessage(role: .system, content: "Answer briefly."),
    ChatMessage(role: .user, content: "What is Swift?")
])
print(response)

// Streaming tokens
let stream = chat.generateStream(messages: [
    ChatMessage(role: .system, content: "Be funny."),
    ChatMessage(role: .user, content: "Tell me a joke")
])
for try await token in stream {
    print(token, terminator: "")
}

let config = ChatSamplingConfig(
    temperature: 0.7,
    topK: 40,
    topP: 0.9,
    maxTokens: 128,
    repetitionPenalty: 1.1
)
let response = try chat.generate(
    messages: [ChatMessage(role: .user, content: "Explain gravity")],
    sampling: config
)

let chat = try await Qwen35MLXChat.fromPretrained()

let history = [
    ChatMessage(role: .system, content: "Remember the user's name."),
    ChatMessage(role: .user, content: "My name is Alex"),
    ChatMessage(role: .assistant, content: "Nice to meet you, Alex!"),
    ChatMessage(role: .user, content: "What's my name?")
]
let response = try chat.generate(messages: history)
print(response)  // "Your name is Alex!"

chat.resetState()  // Clear inference state for a new conversation

// Check memory state
print(chat.isLoaded)        // true
print(chat.memoryFootprint) // 438304768 (~418 MB)

// Free memory under pressure
chat.unload()
print(chat.isLoaded)        // false

// Reload when needed
let chat = try await Qwen35MLXChat.fromPretrained()