Instructions to use UnipatAI/UniMath-35B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use UnipatAI/UniMath-35B-A3B with Transformers:

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

pipe = pipeline("text-generation", model="UnipatAI/UniMath-35B-A3B")
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("UnipatAI/UniMath-35B-A3B")
model = AutoModelForMultimodalLM.from_pretrained("UnipatAI/UniMath-35B-A3B")
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 UnipatAI/UniMath-35B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "UnipatAI/UniMath-35B-A3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "UnipatAI/UniMath-35B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/UnipatAI/UniMath-35B-A3B

SGLang

How to use UnipatAI/UniMath-35B-A3B 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 "UnipatAI/UniMath-35B-A3B" \
    --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": "UnipatAI/UniMath-35B-A3B",
		"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 "UnipatAI/UniMath-35B-A3B" \
        --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": "UnipatAI/UniMath-35B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use UnipatAI/UniMath-35B-A3B with Docker Model Runner:
```
docker model run hf.co/UnipatAI/UniMath-35B-A3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Introduction

We present UniMath-35B-A3B, an open-source olympiad-level mathematical reasoning model with 35 billion total parameters and 3 billion activated per token. Developed by UniPat AI, UniMath-35B-A3B is obtained by further post-training Qwen3.6-35B-A3B on fine-grained proof-synthesis data covering the full arc of a proof: initial attempt, self-critique, obstruction diagnosis, targeted repair, and final synthesis. This activates a reusable self-evolving reasoning capability rather than a fixed answer format, and at test time UniMath-35B-A3B spends additional compute auditing, repairing, and reconciling its own proof attempts instead of resampling blindly. With this test-time self-evolution, UniMath-35B-A3B reaches human gold-medal-contestant level on IMO 2025 (35/42) and USAMO 2026 (36/42), and scores 86.0% on IMO-ProofBench.

More details can be found in our Blog.

Key Features

Fine-Grained Proof-Evolution Data: Training trajectories supervise how a proof changes, not only what the final proof says — an initial route with visible proof obligations, a critical self-assessment naming the first real obstruction, a targeted repair or reroute that preserves earned mathematics, and a final synthesis that fuses drafts, critiques, and surviving routes into one rigorous argument.
Test-Time Self-Evolution: At inference time the model reuses this learned proof-editing loop instead of blind resampling — it samples and self-ranks a pool of candidate proofs, refines the strongest non-perfect candidates by repairing their first real obstruction, and merges surviving proofs so a clean lemma from one route can rescue a stronger route from another.
Adaptive Inference Compute: The self-evolution loop short-circuits straight to synthesis once enough self-verified proofs accumulate, so extra inference budget is spent only where a problem is genuinely hard.

Download

You can download the model then run the inference scripts in https://github.com/UniPat-AI/UniMath.

@misc{unipat2026unimath,
  title   = {UniMath: From Proof-Synthesis Data to Test-Time Self-Evolution},
  author  = {UniPat AI},
  year    = {2026},
  url     = {https://unipat.ai/blog/UniMath},
}

Downloads last month: 324

Safetensors

Model size

36B params

Tensor type

BF16

Model tree for UnipatAI/UniMath-35B-A3B

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

(170)

this model

Quantizations

2 models