Skip to main content
Alibaba

Qwen3.5 9B

trymirai/Qwen3.5-9B-S on Hugging Face
Vendor
Alibaba
Quantization
Mirai-S
Parameters
9B
Size
3.2 GB
$ brew install mirai$ mirai --model trymirai/Qwen3.5-9B-S

Integrate with SDK

1
Choose framework
2
Run the following command to install Mirai SDK
https://github.com/trymirai/uzu
3
Apply code
1import Foundation2import Uzu3​4public 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: "trymirai/Qwen3.5-9B-S") 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        case .toolResults:33            break34        }35    }36    print("Reasoning: \(message?.reasoning() ?? "empty")")37    print("Text: \(message?.text() ?? "empty")")38}

Details

A small, high-quality quantization of Qwen3.5-9B prepared for efficient local inference on Apple silicon.

Mirai Labs

KL divergence versus language-model weight size

Evaluated with romakl on its default set: 20 conversations and 14,399 teacher-generated continuation tokens. This checkpoint: KL 0.0818819; top-1 agreement 90.54%. The plot shows measured checkpoints within ±50% in token-generating weight size, without clipping the selected KL values. The three Bonsai 2 packings were evaluated separately with the Prism runtime. Vision, MTP and speculator weights are excluded from size. KL measures deviation from the base teacher.

Quickstart

If you are on macOS, the easiest way is to install the mirai Homebrew package and then run the CLI:

sh
brew install mirai
mirai --model trymirai/Qwen3.5-9B-S

Currently only Apple silicon inference is supported. If you want to build things from source, read this overview.


Method

Mirai Small uses QTIP-style trellis-coded quantization at about 2.5 bits per weight, with the bits of each matrix chosen from measured KL ablations. Kronecker-structured random rotations are used to reduce weight outliers, and rounding is weighted by a Fisher sketch of the model's own output distribution. The checkpoint was prepared with post-training quantization followed by quantization-aware distillation of the scales.

Citation

If you find our work helpful, feel free to give us a cite.

bibtex
@misc{mirai-quant,
    title  = {{Mirai Quantization}: Redefining the speed-quality frontier for local LLMs on Apple silicon},
    author = {Artur Chakhvadze and Ryan Mathieu and Roman Knyazhitskiy and Nikolai Voinilenko and Chen-Chen Yeh and Artur Mullakhmetov and Eugene Bokhan and others},
    note   = {In collaboration with others at Mirai Labs},
    month  = {June},
    year   = {2026},
    url    = {https://trymirai.com/blog/quantization}
}

Original model

This is a quantized version of Qwen/Qwen3.5-9B. For architecture details, intended use, evaluations, and limitations, see the original model card.

Explore all local models