Instructions to use moot20/Mistral-Small-24B-Base-2501-MLX-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moot20/Mistral-Small-24B-Base-2501-MLX-8bits with Transformers:

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

pipe = pipeline("text-generation", model="moot20/Mistral-Small-24B-Base-2501-MLX-8bits")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("moot20/Mistral-Small-24B-Base-2501-MLX-8bits")
model = AutoModelForCausalLM.from_pretrained("moot20/Mistral-Small-24B-Base-2501-MLX-8bits", device_map="auto")

MLX

How to use moot20/Mistral-Small-24B-Base-2501-MLX-8bits 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("moot20/Mistral-Small-24B-Base-2501-MLX-8bits")

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

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use moot20/Mistral-Small-24B-Base-2501-MLX-8bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moot20/Mistral-Small-24B-Base-2501-MLX-8bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moot20/Mistral-Small-24B-Base-2501-MLX-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/moot20/Mistral-Small-24B-Base-2501-MLX-8bits

SGLang

How to use moot20/Mistral-Small-24B-Base-2501-MLX-8bits 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 "moot20/Mistral-Small-24B-Base-2501-MLX-8bits" \
    --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": "moot20/Mistral-Small-24B-Base-2501-MLX-8bits",
		"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 "moot20/Mistral-Small-24B-Base-2501-MLX-8bits" \
        --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": "moot20/Mistral-Small-24B-Base-2501-MLX-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

MLX LM

How to use moot20/Mistral-Small-24B-Base-2501-MLX-8bits with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Generate some text
mlx_lm.generate --model "moot20/Mistral-Small-24B-Base-2501-MLX-8bits" --prompt "Once upon a time"

Docker Model Runner
How to use moot20/Mistral-Small-24B-Base-2501-MLX-8bits with Docker Model Runner:
```
docker model run hf.co/moot20/Mistral-Small-24B-Base-2501-MLX-8bits
```
Atomic Chat

Mistral-Small-24B-Base-2501-MLX-8bits / README.md

moot20

Add files using upload-large-folder tool

a76a4d0 verified over 1 year ago

preview code

Raw History Blame Contribute Delete

1.16 kB

metadata

language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - zh
  - ja
  - ru
  - ko
license: apache-2.0
library_name: vllm
inference: false
extra_gated_description: >-
  If you want to learn more about how we process your personal data, please read
  our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
tags:
  - transformers
  - mlx
base_model: mistralai/Mistral-Small-24B-Base-2501

moot20/Mistral-Small-24B-Base-2501-MLX-8bits

The Model moot20/Mistral-Small-24B-Base-2501-MLX-8bits was converted to MLX format from mistralai/Mistral-Small-24B-Base-2501 using mlx-lm version 0.21.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("moot20/Mistral-Small-24B-Base-2501-MLX-8bits")

prompt = "hello"

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

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