Instructions to use olka-fi/Mistral-Medium-3.5-128B-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use olka-fi/Mistral-Medium-3.5-128B-MXFP4 with Transformers:

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

pipe = pipeline("text-generation", model="olka-fi/Mistral-Medium-3.5-128B-MXFP4")
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("olka-fi/Mistral-Medium-3.5-128B-MXFP4")
model = AutoModelForMultimodalLM.from_pretrained("olka-fi/Mistral-Medium-3.5-128B-MXFP4")
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

vLLM

How to use olka-fi/Mistral-Medium-3.5-128B-MXFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "olka-fi/Mistral-Medium-3.5-128B-MXFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "olka-fi/Mistral-Medium-3.5-128B-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/olka-fi/Mistral-Medium-3.5-128B-MXFP4

SGLang

How to use olka-fi/Mistral-Medium-3.5-128B-MXFP4 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 "olka-fi/Mistral-Medium-3.5-128B-MXFP4" \
    --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": "olka-fi/Mistral-Medium-3.5-128B-MXFP4",
		"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 "olka-fi/Mistral-Medium-3.5-128B-MXFP4" \
        --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": "olka-fi/Mistral-Medium-3.5-128B-MXFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use olka-fi/Mistral-Medium-3.5-128B-MXFP4 with Docker Model Runner:
```
docker model run hf.co/olka-fi/Mistral-Medium-3.5-128B-MXFP4
```

EAGLE Speculator

by Mitaka-D - opened May 5

Discussion

Mitaka-D

May 5

Thank you for this model variant!

If you use this model with the provided EAGLE speculator ( https://huggingface.co/mistralai/Mistral-Medium-3.5-128B-EAGLE), it won't "accept" the drafted tokens.
According to AI ( I'm no expert 😅 ), the problem is in the activation quantization.

Fix should be to skip it:

"input_activations": null   // ← no activation quantization

olka-fi

Owner May 5

Hi,

Thanks for pointing out!
ATM I don’t have hardware to test speculative setup, but if this fix works for you feel free to open PR 🙂
I’ll verify and merge it

Mitaka-D

May 5

Looks like only changing the config.json won't fix this ...

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment