Instructions to use gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8")
model = AutoModelForImageTextToText.from_pretrained("gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8")
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

vLLM

How to use gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8

SGLang

How to use gdubicki/Devstral-Small-2-24B-Instruct-2512-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 "gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8" \
    --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": "gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8",
		"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 "gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8" \
        --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": "gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8 with Docker Model Runner:
```
docker model run hf.co/gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8
```

gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8

Public mirror of mistralai/Devstral-Small-2-24B-Instruct-2512 — Mistral's official FP8 checkpoint.

This mirror exists to provide a pinned, stable reference for deployment on DGX Spark (GB10). Use the upstream repo if you want to track author updates.

Credits

Base model: mistralai/Devstral-Small-2-24B-Instruct-2512 by Mistral AI
FP8 quantization: by Mistral AI (official release; quant_method: fp8 in config.json)
License: Apache-2.0 (inherited)

Why FP8 (not NVFP4) on GB10

GB10 Blackwell (SM12.1) has native FP8 tensor cores — FP8 GEMM is compute-native
NVFP4 on GB10 runs as W4A16 via Marlin (no CUTLASS FP4 kernel)
Mistral ships official FP8 in this repo → no custom quantization needed
Trade-off vs NVFP4: ~25 GB vs ~12 GB weights; decode ~30% slower (memory-bound)

Model details

Architecture: Mistral3ForConditionalGeneration (multimodal: text + Pixtral vision)
Text backbone: ministral3, 40 layers dense, 24B params
Vision: Pixtral ViT, 24 layers (image-aware; ignored for pure-text usage)
Quantization: FP8 (per-tensor, static activation scheme)
Kept in BF16: vision_tower, multi_modal_projector, lm_head
Max context: 393,216 tokens (YaRN scaling)
SWE-bench Verified: ~55-58% (state-of-art for 24B open-weights SWE agents at release)

Usage

docker run --rm --runtime=nvidia --gpus all \
  -p 8000:8000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  vllm/vllm-openai:cu130-nightly \
  gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8 \
  --dtype auto \
  --kv-cache-dtype fp8 \
  --gpu-memory-utilization 0.30 \
  --max-model-len 131072 \
  --tool-call-parser mistral \
  --enable-auto-tool-choice \
  --enable-chunked-prefill \
  --enable-prefix-caching

Agentic / SWE use case

Devstral is tuned for agentic coding workflows (multi-file edits, tool use, long SWE trajectories) — not raw code-gen from prompt. Pair with Cline / aider / OpenHands.

Downloads last month: 211

Safetensors

Model size

24B params

Tensor type

BF16

F8_E4M3

Model tree for gdubicki/Devstral-Small-2-24B-Instruct-2512-FP8

Base model

mistralai/Mistral-Small-3.1-24B-Base-2503

Quantized

mistralai/Devstral-Small-2-24B-Instruct-2512

Quantized

(34)

this model