Instructions to use caslca/Qwen3.8-27B-static-mixed-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use caslca/Qwen3.8-27B-static-mixed-4bit 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("caslca/Qwen3.8-27B-static-mixed-4bit")
config = load_config("caslca/Qwen3.8-27B-static-mixed-4bit")

# 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
Unsloth Desktop

How to use caslca/Qwen3.8-27B-static-mixed-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "caslca/Qwen3.8-27B-static-mixed-4bit"

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": "caslca/Qwen3.8-27B-static-mixed-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use caslca/Qwen3.8-27B-static-mixed-4bit 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 "caslca/Qwen3.8-27B-static-mixed-4bit"

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 caslca/Qwen3.8-27B-static-mixed-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use caslca/Qwen3.8-27B-static-mixed-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "caslca/Qwen3.8-27B-static-mixed-4bit"

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 "caslca/Qwen3.8-27B-static-mixed-4bit" \
  --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-static-mixed-4bit

27B parameters — text-only in THIS conversion (the upstream base is a VLM; the vision tower was not retained by the text-only convert path) — Hugging Face's size badge undercounts packed 4-bit MLX weights.

MLX static mixed-precision 4-bit quant of unsloth/Qwen3.8-27B. Measured weights footprint: 13.33 GB.

Recommended sampling from a per-model temperature ladder: temperature 0.4 (this recipe failed convergence screens at t0.6; a capped scan located t0.4), top_p 0.95, top_k 20, min_p 0.0, presence_penalty 0.0, thinking ON (budget 81920). Campaign methodology and results: https://github.com/ivan-avramov/mlx_local_stack.

Vision tower restored (2026-08-23)

The original conversion was language-model-only. This revision grafts the vision tower back from the upstream base (unsloth repackaging of the family release): 333 vision_tower.* tensors kept bf16 (exactly what the vision-retaining mlx_vlm convert produces for this family), +0.92 GB.

The text trunk is bit-identical to the evaluated artifact: the trunk shards are byte-copies (md5-verified), and a fixed-token forward pass through the language model produces bit-identical logits pre/post graft. Every benchmark number on this card measures exactly the weights this revision serves for text. One-image smoke passed post-graft.

Downloads last month: 214

Safetensors

Model size

4B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for caslca/Qwen3.8-27B-static-mixed-4bit

Base model

Qwen/Qwen3.8-27B

Finetuned

unsloth/Qwen3.8-27B

Quantized

(3)

this model