Instructions to use Minbyul/AgentMercury-Qwen3.5-35B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Minbyul/AgentMercury-Qwen3.5-35B-A3B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Minbyul/AgentMercury-Qwen3.5-35B-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("Minbyul/AgentMercury-Qwen3.5-35B-A3B")
model = AutoModelForMultimodalLM.from_pretrained("Minbyul/AgentMercury-Qwen3.5-35B-A3B", device_map="auto")
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 Minbyul/AgentMercury-Qwen3.5-35B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Minbyul/AgentMercury-Qwen3.5-35B-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": "Minbyul/AgentMercury-Qwen3.5-35B-A3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Minbyul/AgentMercury-Qwen3.5-35B-A3B

SGLang

How to use Minbyul/AgentMercury-Qwen3.5-35B-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 "Minbyul/AgentMercury-Qwen3.5-35B-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": "Minbyul/AgentMercury-Qwen3.5-35B-A3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Minbyul/AgentMercury-Qwen3.5-35B-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": "Minbyul/AgentMercury-Qwen3.5-35B-A3B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Minbyul/AgentMercury-Qwen3.5-35B-A3B with Docker Model Runner:
```
docker model run hf.co/Minbyul/AgentMercury-Qwen3.5-35B-A3B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

AgentMercury-Qwen3.5-35B-A3B

AgentMercury-Qwen3.5-35B-A3B is a Qwen3.5-35B-A3B (multimodal Mixture-of-Experts, Qwen3_5MoeForConditionalGeneration) checkpoint post-trained with agentic reinforcement learning on MCP (Model-Context-Protocol) tool-use environments. The RL objective rewards completing real multi-turn agent tasks (correct tool calls, correct final database/environment state), not just producing text.

This is the 35B-A3B member of the AgentMercury family; the smaller sibling is Minbyul/AgentMercury-Qwen3.5-4B.

Highlights

Base: Qwen3.5-35B-A3B (text + vision) — 35B total parameters, 3B activated per token, 256 experts (8 routed + 1 shared), 40 layers of hybrid Gated DeltaNet / gated attention, 262,144 native context.
Method: on-policy GRPO, fully-asynchronous MCP agentic RL (disjoint trainer / sglang rollout GPUs, 2 nodes × 8 GPUs).
Reward: final environment-state verifiers on real agent tasks (tool correctness + DB checks), with penalties for degeneration/truncation.
Rollout budget: global batch 128 (16 prompts × 8 samples), up to 20 tool-use turns and 24,576 response tokens per trajectory, constant LR 1e-6.
Training set: 38,670 create/update/delete agent tasks drawn from 3,950 distinct synthetic MCP environments.

Usage

Serving (sglang, recommended — matches evaluation)

python3 -m sglang.launch_server \
  --model-path Minbyul/AgentMercury-Qwen3.5-35B-A3B \
  --served-model-name agentmercury-qwen3.5-35b-a3b \
  --host 0.0.0.0 --port 30000 --tp-size 1 \
  --context-length 131072 --mem-fraction-static 0.85 \
  --moe-runner-backend triton --attention-backend triton \
  --reasoning-parser qwen3 --tool-call-parser qwen3_coder \
  --trust-remote-code

Then call the OpenAI-compatible endpoint at http://localhost:30000/v1 (supports tool calls).

Serve with at least a 128K context window. Like its base model, this checkpoint thinks before it answers; a short context window truncates generations inside the reasoning block and turns them into empty responses, which silently degrades any downstream score.

transformers

from transformers import AutoModelForCausalLM, AutoProcessor
model = AutoModelForCausalLM.from_pretrained(
    "Minbyul/AgentMercury-Qwen3.5-35B-A3B",
    torch_dtype="bfloat16", device_map="auto", trust_remote_code=True,
)
processor = AutoProcessor.from_pretrained(
    "Minbyul/AgentMercury-Qwen3.5-35B-A3B", trust_remote_code=True,
)

Training notes

These weights are the rollout-99 checkpoint of a 200-rollout MCP agentic RL run. Benchmark results for this checkpoint are not included in this card.