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

Libraries

How to use caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-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-Fable-Distill-mlx-uniform-4bit")
config = load_config("caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-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)

Transformers

How to use caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit")
model = AutoModelForMultimodalLM.from_pretrained("caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit

SGLang

How to use caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop

How to use caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-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-Fable-Distill-mlx-uniform-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-Fable-Distill-mlx-uniform-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit with Docker Model Runner:
```
docker model run hf.co/caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit
```

Hermes Agent

How to use caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-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-Fable-Distill-mlx-uniform-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-Fable-Distill-mlx-uniform-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-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-Fable-Distill-mlx-uniform-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-Fable-Distill-mlx-uniform-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-Fable-Distill-mlx-uniform-4bit

27B (VLM) parameters — note: Hugging Face's size badge undercounts packed 4-bit MLX weights (it counts the packed uint32 tensors), so the number shown beside this repo is wrong; the figure here is the true parameter count.

MLX uniform 4-bit quant of TeichAI/Qwen3.8-27B-Fable-Distill.

measured	value
effective bits/weight	4.0 (uniform; all 498 quantized layers at 4-bit)
weights footprint	16.05 GB
quantized-layer bit histogram	4-bit: 498

Recommended sampling (measured, not vibes)

param	value
temperature	0.6 (certified by a per-model temperature ladder)
top_p / top_k / min_p	0.95 / 20 / 0.0
presence_penalty	0.0
max_tokens / thinking_budget	102400 / 81920 (thinking ON)

These values were certified by an execution-gated benchmark campaign (temperature ladders with convergence gates over HumanEval+/MBPP+ and agentic harnesses) — methodology and full results: https://github.com/ivan-avramov/mlx_local_stack.

Serving: MLX (mlx-lm / mlx-vlm). Quantized on-device with mlx_lm.convert (uniform) or mlx_optiq (mixed-precision KL-sensitivity recipes).

Downloads last month: 245

Safetensors

Model size

27B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit

Base model

Qwen/Qwen3.8-27B

Finetuned

TeichAI/Qwen3.8-27B-Fable-Distill

Quantized

(8)

this model

caslca
/

Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit

Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit

Recommended sampling (measured, not vibes)

Model tree for caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit

Datasets used to train caslca/Qwen3.8-27B-Fable-Distill-mlx-uniform-4bit