Vendor
Meta
Parameters
30B
Size
51.9 GB
$ brew install mirai$ mirai --model meta-models/Muse-Glimmer-30B

Integrate with SDK

1
Choose framework
2
Run the following command to install Mirai SDK
https://github.com/trymirai/uzu-swift
3
Apply code
1import Foundation2import Uzu34public func runChat() async throws {5    let engineConfig = EngineConfig.create()6    let engine = try await Engine.create(config: engineConfig)7    8    guard let model = try await engine.model(identifier: "alibaba:qwen3.5:0.8b:mirai:mirai-m:4") else {9        return10    }11    for try await update in try await engine.download(model: model).iterator() {12        print(String(format: "\r\u{001B}[2KDownload progress: %.2f%%", update.progress() * 100), terminator: "")13        fflush(stdout)14    }15    print()16    17    let messages = [18        ChatMessage.system().withText(text: "You are a helpful assistant"),19        ChatMessage.user().withText(text: "Tell me a short, funny story about a robot")20    ]21    let session = try await engine.chat(model: model, config: .create())22    let stream = await session.replyWithStream(input: messages, config: .create())23    var message: ChatMessage? = nil24    for try await update in stream.iterator() {25        switch update {26        case .replies(let replies):27            let reply = replies.last28            message = reply?.message29            print("Generated tokens: \(reply?.stats.tokensCountOutput ?? 0)")30        case .error(let error):31            print("Error: \(error)")32        }33    }34    print("Reasoning: \(message?.reasoning() ?? "empty")")35    print("Text: \(message?.text() ?? "empty")")36}37

Details

Muse Glimmer-30B is Meta's Apache-2.0-licensed, 30-billion-parameter causal language model with a dedicated perception encoder. Distilled from Muse Spark and designed for local autonomous agents, it combines multimodal understanding, multi-step reasoning, schema-based tool use, and failure recovery for consumer hardware.

The model accepts interleaved text and images and produces text across a 131,072-token context window. Its chat format supports separate reasoning, tool, and user channels, with controllable reasoning strengths of low, medium, high, and xhigh. Meta reports training coverage across more than 100 languages.

Explore all local models