Instructions to use liodon-ai/Mistral-7B-v0.1-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liodon-ai/Mistral-7B-v0.1-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="liodon-ai/Mistral-7B-v0.1-FP8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("liodon-ai/Mistral-7B-v0.1-FP8")
model = AutoModelForCausalLM.from_pretrained("liodon-ai/Mistral-7B-v0.1-FP8", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liodon-ai/Mistral-7B-v0.1-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liodon-ai/Mistral-7B-v0.1-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liodon-ai/Mistral-7B-v0.1-FP8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liodon-ai/Mistral-7B-v0.1-FP8

SGLang

How to use liodon-ai/Mistral-7B-v0.1-FP8 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 "liodon-ai/Mistral-7B-v0.1-FP8" \
    --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": "liodon-ai/Mistral-7B-v0.1-FP8",
		"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 "liodon-ai/Mistral-7B-v0.1-FP8" \
        --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": "liodon-ai/Mistral-7B-v0.1-FP8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liodon-ai/Mistral-7B-v0.1-FP8 with Docker Model Runner:
```
docker model run hf.co/liodon-ai/Mistral-7B-v0.1-FP8
```

Mistral-7B-v0.1-FP8 / README.md

PY-AI-Dev

Add FP8 (dynamic) quantization for Mistral-7B-v0.1

7356f46 verified 14 days ago

preview code

Raw

History Blame Contribute Delete

2.1 kB

	---
	license: other
	base_model: mistralai/Mistral-7B-v0.1
	base_model_relation: quantized
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- fp8
	- compressed-tensors
	- vllm
	- quantized
	quantized_by: liodon-ai
	---

	# Mistral-7B-v0.1 — FP8 (dynamic)

	FP8 quantization of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1), published by [Liodon AI](https://huggingface.co/liodon-ai).

	Quantized with [llm-compressor](https://github.com/vllm-project/llm-compressor) using the
	`FP8_DYNAMIC` scheme: weights are cast to FP8 (E4M3) per-channel ahead of time, activations are
	quantized to FP8 dynamically per-token at inference time. No calibration dataset is needed for this
	scheme, so the quantized weights are numerically just a direct cast of the original — no calibration-set
	bias to worry about. `lm_head` is left unquantized (standard practice — negligible size, disproportionate
	quality impact if quantized).

	Original size: 14.5 GB → Quantized: 7.5 GB.

	## Quick Start

	vLLM
	```bash
	vllm serve liodon-ai/Mistral-7B-v0.1-FP8
	```

	Text Generation Inference (TGI)
	```bash
	docker run --gpus all -p 8080:80 ghcr.io/huggingface/text-generation-inference \
	--model-id liodon-ai/Mistral-7B-v0.1-FP8
	```

	SGLang
	```bash
	python -m sglang.launch_server --model-path liodon-ai/Mistral-7B-v0.1-FP8
	```

	FP8 execution requires an NVIDIA GPU with compute capability ≥ 8.9 (Ada/Hopper/Blackwell — RTX 40-series,
	L4/L40S, H100/H200, B100/B200/GB10). On older GPUs, vLLM/TGI will dequantize to run, which loses the
	speed/memory benefit.

	## Source

	- Model: [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
	- License: other

	## Citation

	```bibtex
	@misc{liodonai_mistral_7b_v0_1_fp8,
	title = {Mistral-7B-v0.1 — FP8},
	author = {{Liodon AI}},
	year = {2026},
	howpublished = {\url{https://huggingface.co/liodon-ai/Mistral-7B-v0.1-FP8}},
	note = {FP8 (dynamic) quantization of mistralai/Mistral-7B-v0.1}
	}
	```

	---
	Quantized by [Liodon AI](https://huggingface.co/liodon-ai)