Instructions to use treeish/Qwen3.8-27B-oQ3e-MTP-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use treeish/Qwen3.8-27B-oQ3e-MTP-MLX with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("treeish/Qwen3.8-27B-oQ3e-MTP-MLX")
config = load_config("treeish/Qwen3.8-27B-oQ3e-MTP-MLX")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use treeish/Qwen3.8-27B-oQ3e-MTP-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "treeish/Qwen3.8-27B-oQ3e-MTP-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "treeish/Qwen3.8-27B-oQ3e-MTP-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use treeish/Qwen3.8-27B-oQ3e-MTP-MLX with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "treeish/Qwen3.8-27B-oQ3e-MTP-MLX"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default treeish/Qwen3.8-27B-oQ3e-MTP-MLX

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use treeish/Qwen3.8-27B-oQ3e-MTP-MLX with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "treeish/Qwen3.8-27B-oQ3e-MTP-MLX"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "treeish/Qwen3.8-27B-oQ3e-MTP-MLX" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.8-27B-oQ3e-MTP-MLX

This is the Qwen3.8-27B model package used by Sprig in Treeish. It combines an oQ3e mixed-precision MLX quant with its embedded Multi-Token Prediction head and the chat template used for Sprig's coding-agent workflow.

The package is ready to download and load as-is. Treeish pins an exact repository commit rather than following main.

Model

Base model: Qwen/Qwen3.8-27B
Architecture: 27B dense parameters
Quantisation: oQ3e imatrix-enhanced mixed precision
Default quantisation: 3-bit affine, group size 64
Per-tensor overrides: 4, 5 and 6-bit, with group size 64
Format: MLX safetensors
MTP: 1 embedded layer under language_model.mtp.*
Context length: 262,144 tokens

The package contains 2,209 indexed tensors, including 333 vision-tower tensors and 29 embedded MTP tensors. Its 3 weight shards contain 13,785,495,056 bytes of tensor data.

Provenance

The quantised weights, model configuration and oQ calibration report are byte-identical to mlx-works/Qwen3.8-27B-oQ3e-mtp at commit 6a3f3c74a14d2fcba565ad8d5b11aff52b522f42. The source declares oMLX 0.5.7 as the converter and Qwen/Qwen3.8-27B as the base model. Its imatrix report records 128 samples of 512 tokens from oqe_code_multilingual, with 503 of 504 entries applied. It does not identify the exact base-model commit used for conversion, so this is a curated, byte-pinned distribution rather than a byte-reproducible conversion recipe.

The chat template is Froggeric's v22.5 template. It is byte-identical to chat_template.jinja in froggeric/Qwen-Fixed-Chat-Templates at commit 855bffc49448e299789730ff92c9b8d834d6cc14.

No model, tokenizer or configuration tensors were changed for this release. The release replaces the chat template and adds the licence, provenance and file manifest. tokenizer_config.json is taken from Qwen/Qwen3.8-27B at commit 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0.

Runtime compatibility

This package is built for Treeish's pinned MLX Swift runtime. A different runtime must support the per-tensor quantisation overrides in config.json and the embedded Qwen MTP layout.

Treeish uses this model from 36 GB of unified memory and recommends 48 GB. Headroom depends on context length, cache settings and other running applications.

Treeish validation

Treeish's release benchmark has not yet been run on this package. RELEASE_MANIFEST.json records the release status and is updated when it has.

Limitations

Quantisation trades some model quality for memory use and local generation speed. Applications should validate the model against their own prompts, tool format and runtime.

The model package contains no custom executable code. File sizes, SHA-256 digests and source revisions are recorded in RELEASE_MANIFEST.json.

Licence

Qwen3.8-27B is licensed under Apache 2.0. The full licence text is included in LICENSE. The Froggeric template repository also declares Apache 2.0 and is attributed above.

Downloads last month: 82

Safetensors

Model size

28B params

Tensor type

U32

BF16

MLX

Hardware compatibility

3-bit

Model tree for treeish/Qwen3.8-27B-oQ3e-MTP-MLX

Base model

Qwen/Qwen3.8-27B

Quantized

(1202)

this model