Instructions to use GGorman/WizardCoder-33B-V1.1-Q8-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GGorman/WizardCoder-33B-V1.1-Q8-mlx with Transformers:

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

pipe = pipeline("text-generation", model="GGorman/WizardCoder-33B-V1.1-Q8-mlx")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GGorman/WizardCoder-33B-V1.1-Q8-mlx")
model = AutoModelForCausalLM.from_pretrained("GGorman/WizardCoder-33B-V1.1-Q8-mlx")

MLX

How to use GGorman/WizardCoder-33B-V1.1-Q8-mlx with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm
# if on a CUDA device, also pip install mlx[cuda]

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

model, tokenizer = load("GGorman/WizardCoder-33B-V1.1-Q8-mlx")

prompt = "Once upon a time in"
text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use GGorman/WizardCoder-33B-V1.1-Q8-mlx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GGorman/WizardCoder-33B-V1.1-Q8-mlx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GGorman/WizardCoder-33B-V1.1-Q8-mlx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GGorman/WizardCoder-33B-V1.1-Q8-mlx

SGLang

How to use GGorman/WizardCoder-33B-V1.1-Q8-mlx 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 "GGorman/WizardCoder-33B-V1.1-Q8-mlx" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GGorman/WizardCoder-33B-V1.1-Q8-mlx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "GGorman/WizardCoder-33B-V1.1-Q8-mlx" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GGorman/WizardCoder-33B-V1.1-Q8-mlx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use GGorman/WizardCoder-33B-V1.1-Q8-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "GGorman/WizardCoder-33B-V1.1-Q8-mlx" --prompt "Once upon a time"

Docker Model Runner
How to use GGorman/WizardCoder-33B-V1.1-Q8-mlx with Docker Model Runner:
```
docker model run hf.co/GGorman/WizardCoder-33B-V1.1-Q8-mlx
```

GGorman/WizardCoder-33B-V1.1-Q8-mlx

The Model GGorman/WizardCoder-33B-V1.1-Q8-mlx was converted to MLX format from WizardLMTeam/WizardCoder-33B-V1.1 using mlx-lm version 0.19.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("GGorman/WizardCoder-33B-V1.1-Q8-mlx")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

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

Downloads last month: 30

Safetensors

Model size

9B params

Tensor type

F16

U32

MLX

Hardware compatibility

8-bit

Model tree for GGorman/WizardCoder-33B-V1.1-Q8-mlx

Base model

WizardLMTeam/WizardCoder-33B-V1.1

Quantized

(10)

this model

Evaluation results

pass@1 on HumanEval
self-reported

0.799