Instructions to use Open4bits/Qwen3-14B-Base-mlx-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Open4bits/Qwen3-14B-Base-mlx-fp16 with Transformers:

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

pipe = pipeline("text-generation", model="Open4bits/Qwen3-14B-Base-mlx-fp16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Open4bits/Qwen3-14B-Base-mlx-fp16")
model = AutoModelForCausalLM.from_pretrained("Open4bits/Qwen3-14B-Base-mlx-fp16", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use Open4bits/Qwen3-14B-Base-mlx-fp16 with MLX:

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

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Open4bits/Qwen3-14B-Base-mlx-fp16")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use Open4bits/Qwen3-14B-Base-mlx-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Open4bits/Qwen3-14B-Base-mlx-fp16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Open4bits/Qwen3-14B-Base-mlx-fp16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Open4bits/Qwen3-14B-Base-mlx-fp16

SGLang

How to use Open4bits/Qwen3-14B-Base-mlx-fp16 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 "Open4bits/Qwen3-14B-Base-mlx-fp16" \
    --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": "Open4bits/Qwen3-14B-Base-mlx-fp16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Open4bits/Qwen3-14B-Base-mlx-fp16" \
        --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": "Open4bits/Qwen3-14B-Base-mlx-fp16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

How to use Open4bits/Qwen3-14B-Base-mlx-fp16 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Open4bits/Qwen3-14B-Base-mlx-fp16"

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": "Open4bits/Qwen3-14B-Base-mlx-fp16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use Open4bits/Qwen3-14B-Base-mlx-fp16 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Open4bits/Qwen3-14B-Base-mlx-fp16"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Open4bits/Qwen3-14B-Base-mlx-fp16"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Open4bits/Qwen3-14B-Base-mlx-fp16",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use Open4bits/Qwen3-14B-Base-mlx-fp16 with Docker Model Runner:
```
docker model run hf.co/Open4bits/Qwen3-14B-Base-mlx-fp16
```

Hermes Agent

How to use Open4bits/Qwen3-14B-Base-mlx-fp16 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 "Open4bits/Qwen3-14B-Base-mlx-fp16"

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 Open4bits/Qwen3-14B-Base-mlx-fp16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Open4bits/Qwen3-14B-Base-mlx-fp16 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Open4bits/Qwen3-14B-Base-mlx-fp16"

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 "Open4bits/Qwen3-14B-Base-mlx-fp16" \
  --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"

fmasterpro27 commited on Feb 14

Commit

b5609f9

verified ·

1 Parent(s): 2ddd319

Update README.md

Browse files

Files changed (1) hide show

README.md +65 -1

README.md CHANGED Viewed

@@ -6,4 +6,68 @@ tags:
 - open4bits
 base_model: Qwen/Qwen3-14B-Base
 pipeline_tag: text-generation
----

 - open4bits
 base_model: Qwen/Qwen3-14B-Base
 pipeline_tag: text-generation
+---
+Here’s a professional **GitHub-ready `README.md`** for **Open4bits/Qwen3-14B-Base-MLX-FP16**:
+---
+# Open4bits / Qwen3-14B-Base-MLX-FP16
+This repository provides the **Qwen3-14B Base model converted to MLX format with FP16 precision**, published by Open4bits to enable efficient high-performance inference with reduced memory usage and broad hardware compatibility.
+The underlying Qwen3-14B model and architecture are **developed and owned by the original creators**. This repository contains an FP16 precision MLX conversion of the original model weights.
+Open4bits has started supporting **MLX models** to broaden compatibility with emerging quantization formats and efficient runtimes, allowing improved performance on a range of platforms.
+---
+## Model Overview
+**Qwen3-14B Base** is a 14-billion parameter transformer-based language model designed for strong general understanding, reasoning, and instruction following.
+This release uses **FP16 precision** in **MLX format**, enabling efficient inference with balanced speed and quality.
+---
+## Model Details
+* **Base Model:** Qwen3-14B
+* **Precision:** FP16 (float16)
+* **Format:** MLX
+* **Task:** Text generation, instruction following
+* **Weight tying:** Preserved
+* **Compatibility:** MLX-enabled inference engines and runtimes
+The FP16 format provides improved performance and reduced memory consumption compared to full FP32 precision while retaining high generation quality.
+---
+## Intended Use
+This model is intended for:
+* High-performance text generation and conversational applications
+* CPU-based or accelerator-supported deployments
+* Research, experimentation, and prototyping
+* Offline or self-hosted AI systems
+---
+## Limitations
+* Lower precision compared to non-quantized models
+* Output quality depends on prompt design and inference parameters
+* Not optimized for highly specialized domain-specific tasks without further fine-tuning
+---
+## License
+This model follows the **Apache 2.0** of the base Qwen3-14B model.
+Users must comply with the licensing conditions defined by the original model creators.
+---
+## Support
+If you find this model useful, please consider supporting the project.
+Your support helps Open4bits continue releasing and maintaining high-quality efficient models for the community.