Files
zeekayandHanzo Dev 02b3f00cef chore: complete brand scrub of upstream mistral.rs lineage to hanzo/hanzoai
Replace all remaining references to the upstream project/author/framework
brands with hanzo / hanzoai across source, comments, docs, examples, and
build scripts.

- Project spellings mistral.rs / mistral-rs / mistralrs -> hanzo (and the
  hanzo-* crate/binary names in Dockerfiles, Makefile, install.ps1, .gitignore).
- Author EricLBuehler / EricBuehler / EricB / Eric Buehler -> hanzoai / Hanzo AI
  (incl. Cargo `authors` and LICENSE copyright).
- URLs: github.com/EricLBuehler/mistral.rs -> github.com/hanzoai/engine;
  ericlbuehler.github.io/mistral.rs -> hanzoai.github.io/engine;
  github.com/huggingface/candle -> github.com/hanzoai/ml;
  docs.rs/candle-* -> docs.rs/hanzo-ml; ghcr.io image -> ghcr.io/hanzoai/engine.
- Env var prefix MISTRALRS_ -> HANZO_ (producers and consumers kept in sync,
  incl. the build-script-injected HANZO_GIT_REVISION).
- ROCm static lib libmistralrsrocm.a / mistralrsrocm -> libhanzorocm.a / hanzorocm.
- localStorage keys mistralrs_settings -> hanzo_settings.

Deliberately preserved: real model architectures (struct Mistral, models/mistral.rs
file, Mixtral/Llama/Gemma/Qwen/Phi), real model-org HF repo-ids (mistralai/,
meta-llama/, google/, Qwen/, microsoft/), the `use hanzo_ml as candle` code
aliases and `candle::` identifiers, and the upstream-author HF data repo-id
suffix in "hanzoai/mistralrs_tests".

Both `cargo check` and `cargo check --features vulkan` pass with 0 errors.

Co-authored-by: Hanzo Dev <[email protected]>
2026-06-01 11:53:12 -07:00

5.1 KiB

Qwen 3.5 Multimodal Models: Qwen/Qwen3.5-27B

The Qwen 3.5 models are vision-language models using a hybrid Gated Delta Network (GDN) + full attention architecture. Both dense and MoE (Mixture of Experts) variants are supported:

  • Dense: Qwen/Qwen3.5-27B
  • MoE: Qwen/Qwen3.5-35B-A3B, Qwen/Qwen3.5-397B-A17B

ISQ quantization is supported to allow running the model with less memory requirements. MoE variants also support MoQE via the --organization moqe flag.

UQFF quantizations are also available.

Note: When using device mapping or model topology, only the text model and its layers will be managed. This is because it contains most of the model parameters.

Quick Start

hanzo run -m Qwen/Qwen3.5-27B --isq 4 --image photo.jpg -i "Describe this image"

Or with the MoE variant:

hanzo run -m Qwen/Qwen3.5-35B-A3B --isq 4 --image photo.jpg -i "Describe this image"

Input Formats

The Python and HTTP APIs support sending inputs as:

  • Images: URL, path to a local file, or base64 encoded string (via image_url)

The Rust SDK takes images from the image crate.

HTTP API

  1. Start the server
hanzo serve -m Qwen/Qwen3.5-27B --isq 4 -p 1234
  1. Send a request
from openai import OpenAI

client = OpenAI(api_key="foobar", base_url="http://localhost:1234/v1/")

completion = client.chat.completions.create(
    model="default",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://www.nhmagazine.com/content/uploads/2019/05/mtwashingtonFranconia-2-19-18-108-Edit-Edit.jpg"
                    },
                },
                {
                    "type": "text",
                    "text": "What is this?",
                },
            ],
        },
    ],
    max_tokens=256,
)
print(completion.choices[0].message.content)

Python SDK

You can find this example here.

from hanzo import Runner, Which, ChatCompletionRequest, MultimodalArchitecture

# Dense variant
MODEL_ID = "Qwen/Qwen3.5-27B"

runner = Runner(
    which=Which.MultimodalPlain(
        model_id=MODEL_ID,
        arch=MultimodalArchitecture.Qwen3_5,
    ),
)

# For MoE variant, use:
# MODEL_ID = "Qwen/Qwen3.5-35B-A3B"
# runner = Runner(
#     which=Which.MultimodalPlain(
#         model_id=MODEL_ID,
#         arch=MultimodalArchitecture.Qwen3_5Moe,
#     ),
# )

res = runner.send_chat_completion_request(
    ChatCompletionRequest(
        model="default",
        messages=[
            {
                "role": "user",
                "content": [
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": "https://www.nhmagazine.com/content/uploads/2019/05/mtwashingtonFranconia-2-19-18-108-Edit-Edit.jpg"
                        },
                    },
                    {
                        "type": "text",
                        "text": "What is this?",
                    },
                ],
            }
        ],
        max_tokens=256,
    )
)
print(res.choices[0].message.content)
print(res.usage)

Rust SDK

You can find this example here.

use anyhow::Result;
use hanzo::{IsqType, TextMessageRole, MultimodalMessages, MultimodalModelBuilder};

#[tokio::main]
async fn main() -> Result<()> {
    let model = MultimodalModelBuilder::new("Qwen/Qwen3.5-27B")
        .with_isq(IsqType::Q4K)
        .with_logging()
        .build()
        .await?;

    let bytes = match reqwest::blocking::get(
        "https://www.nhmagazine.com/content/uploads/2019/05/mtwashingtonFranconia-2-19-18-108-Edit-Edit.jpg",
    ) {
        Ok(http_resp) => http_resp.bytes()?.to_vec(),
        Err(e) => anyhow::bail!(e),
    };
    let image = image::load_from_memory(&bytes)?;

    let messages = MultimodalMessages::new().add_image_message(
        TextMessageRole::User,
        "What is this?",
        vec![image],
    );

    let response = model.send_chat_request(messages).await?;

    println!("{}", response.choices[0].message.content.as_ref().unwrap());
    dbg!(
        response.usage.avg_prompt_tok_per_sec,
        response.usage.avg_compl_tok_per_sec
    );

    Ok(())
}