Instructions to use amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3 with Transformers:

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

pipe = pipeline("text-generation", model="amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3

SGLang

How to use amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3 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 "amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3" \
    --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": "amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3",
		"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 "amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3" \
        --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": "amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3 with Docker Model Runner:
```
docker model run hf.co/amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3
```

ExLlamaV3 quantizations of Devstral-2-123B-Instruct-2512 with tensor-level (L3) optimization. Maximum effort applied towards the goal of achieving the best possible quantizations at the expense of time and compute.

Using this measurement.json file and the base quants provided, additional highly-optimized quantizations can be made in seconds at any reasonable bpw by anyone. All work done with ExLlamaV3 v0.0.18.

Optimized

VRAM-targeted quants using exl3's measure.py → optimize.py pipeline.

	Size	bpw	Target
3.20bpw-h6-opt	50 GB	3.20	72GB @ 256k
3.90bpw-h6-opt	60 GB	3.90	72GB @ 128k
4.75bpw-h6-opt	72 GB	4.75	96GB @ 256k
5.45bpw-h6-opt	82 GB	5.45	96GB @ 128k
5.70bpw-h6-opt	85 GB	5.70	128GB @ 256k

The 5.70bpw quant hit the optimization ceiling - requesting 6.75bpw produced 5.70bpw output, indicating no further beneficial tensor swaps available.

Base

	Size	bpw
3.0bpw-h6	47 GB	3.0
4.0bpw-h6	61 GB	4.0
5.0bpw-h6	76 GB	5.0
6.0bpw-h6	90 GB	6.0
7.0bpw-h6	104 GB	7.0

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for amanwalksdownthestreet/Devstral-2-123B-Instruct-2512-exl3

Base model

mistralai/Devstral-2-123B-Instruct-2512

Quantized

(18)

this model