Instructions to use SupraLabs/Supra2.5-Pro-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SupraLabs/Supra2.5-Pro-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SupraLabs/Supra2.5-Pro-Instruct") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SupraLabs/Supra2.5-Pro-Instruct") model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra2.5-Pro-Instruct", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use SupraLabs/Supra2.5-Pro-Instruct with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M # Run inference directly in the terminal: llama cli -hf SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M # Run inference directly in the terminal: llama cli -hf SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M
Use Docker
docker model run hf.co/SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use SupraLabs/Supra2.5-Pro-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SupraLabs/Supra2.5-Pro-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SupraLabs/Supra2.5-Pro-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M
- SGLang
How to use SupraLabs/Supra2.5-Pro-Instruct 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 "SupraLabs/Supra2.5-Pro-Instruct" \ --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": "SupraLabs/Supra2.5-Pro-Instruct", "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 "SupraLabs/Supra2.5-Pro-Instruct" \ --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": "SupraLabs/Supra2.5-Pro-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use SupraLabs/Supra2.5-Pro-Instruct with Ollama:
ollama run hf.co/SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use SupraLabs/Supra2.5-Pro-Instruct with Docker Model Runner:
docker model run hf.co/SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M
- Lemonade
How to use SupraLabs/Supra2.5-Pro-Instruct with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull SupraLabs/Supra2.5-Pro-Instruct:Q4_K_M
Run and chat with the model
lemonade run user.Supra2.5-Pro-Instruct-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download README.md from SupraLabs/Supra2.5-Pro-Instruct: direct link, hf CLI and curl.
- Browser
- Download file 3.21 kB
-
https://huggingface.co/SupraLabs/Supra2.5-Pro-Instruct/resolve/main/README.md
- Command line
-
hf download hf://SupraLabs/Supra2.5-Pro-Instruct/README.md
-
curl -L -o README.md https://huggingface.co/SupraLabs/Supra2.5-Pro-Instruct/resolve/main/README.md
license: apache-2.0
viewer: false
language:
- en
pipeline_tag: text-generation
library_name: transformers
tags:
- small
- tiny
- supra
- supra2-5
- supra2.5
- qwen3
- efficient
- instruct
- chat
- conversational
- chatbot
- gpt
Supra2.5-Pro Instruct
Ultra-efficient instruction-tuned model • 65M Parameters • Next-generation Supra
Supra2.5-Pro Instruct is the instruction-tuned version of Supra2.5-Pro-Base and is ready to use for local chat inference.
Note that this model was not safety-aligned or preference optimized in any way - so built your own safety filter in front of it before presenting answers to users.
Examples
User: What is AI?
Supra: Artificial intelligence (AI) is the ability of computers to perform tasks that normally require human intelligence—like understanding language, recognizing images, solving problems, or making decisions. It includes subfields like machine learning, natural language processing, and robotics. Most current AI is still in its infancy, but advances in hardware, software, and training make it useful for a wide range of applications.
User: How are you?
Supra: I'm running well, thanks for asking! 😊 As a compact language model, I don't have feelings or memory across separate chats. What can I help you with today?
User: Who was Albert Einstein and what was he famous for?
Supra: Albert Einthoven (1879–1955) was a German-born theoretical physicist, widely regarded as one of the greatest scientists of all time. He is best known for his theory of general relativity, which formalized the three-dimensional spacetime curvature that underlies our universe.
He is widely credited with inventing the first practical, mass-produced gravity device, the Einstein telescope (catastrophe), and earning the 1921 Nobel Prize in Physics for his work on gravitational waves.
- Famous for: his work Gravity (1905), The Elements of Classical Mechanics (book), and On Relativity (reprint).
- His contributions to physics are celebrated for grounding modern physics in fundamental physics.
charsetensures correct text encoding.requiredprevents empty input.type="password"protects against guessing credentials.
Data
We finetuned the base model for 2 epochs on nearly 9000 synthetically generated conversations by DeepSeek V4.1 Flash 1017 (non-reasoning via DeepSeek API).
Prompt-Source for a lot of prompts: SmolTalk2
What this model can do
- basic chat, coding & math
- everyday conversations
Usage
You can run the model nearly the same was as Supra2-Medium-Instruct. The chat template is the same (basic ChatML).
GGUFs in F16, Q8_0 and Q4_K_M are also available!
What's next
At SupraLabs, we are heavily developing the next architectures, improving our models and hoping to give you the next best model soon! Give us a follow and a like on Hugging Face if you want to support our work.
© SupraLabs 2026
