Instructions to use Orvena/Orvena-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Orvena/Orvena-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Orvena/Orvena-4B")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Orvena/Orvena-4B")
model = AutoModelForMultimodalLM.from_pretrained("Orvena/Orvena-4B", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Orvena/Orvena-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Orvena/Orvena-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Orvena/Orvena-4B",
		"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/Orvena/Orvena-4B

SGLang

How to use Orvena/Orvena-4B 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 "Orvena/Orvena-4B" \
    --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": "Orvena/Orvena-4B",
		"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 "Orvena/Orvena-4B" \
        --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": "Orvena/Orvena-4B",
		"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 Orvena/Orvena-4B with Docker Model Runner:
```
docker model run hf.co/Orvena/Orvena-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Orvena 4B

Orvena 4B is the language model behind Orvena, a private assistant that runs on the iPhone. It is trained for what an assistant actually does with a phone: reading the calendar, setting alarms and reminders, finding places and how long it takes to get there, searching the web, and working with the services people connect over MCP, such as Notion, Todoist, Airtable and Gmail. It works in 30 languages and answers without a separate thinking step, which keeps it quick on a phone.

This repository holds the bf16 weights, including a retrained multi-token prediction (MTP) head. The 4-bit MLX build that the Orvena app downloads is Orvena/Orvena-4B-MLX-4bit. The technical report covers the data, training and evaluation in full.

How it is built

The training data is built around a simulated iPhone that exposes Orvena's real tool catalog and MCP servers whose tool lists were captured from Notion, Linear, GitHub, Todoist, Airtable, Atlassian, Gmail, Google Drive, Google Calendar, Granola, Home Assistant and Zapier. Each scenario is a request together with the phone's data (calendar, contacts, reminders, places, weather, health) and checks on the calls the assistant should make and what its answer must contain. Only answers that passed the checks were kept. Of the 3,397 scenarios, Qwen3.6-35B-A3B answered 1,126 with thinking off and 724 with thinking on, and the base model itself answered 1,547. That gives 11,161 rounds, one per model call, of which 574 were held out for validation.

Two smaller sets keep the model from overreaching: requests no tool can do and plain questions asked with connections installed, so it learns to answer or say what it can't do; and 600 instruction-following examples (IFEval-style prompts from argilla/ifeval-like-data, answered by the base model and kept only when IFEval's checker passed), so it still follows formatting instructions like the base model does.

Orvena 4B keeps the architecture of its base model, Qwen3.5-4B: 24 Gated DeltaNet layers, 8 full-attention layers and the vision encoder. A LoRA adapter (rank 16, alpha 320) on all 248 linear layers of the language model was trained for one epoch and merged into these weights.

All of it was trained with thinking off, and the chat template in this repository answers without thinking unless you pass enable_thinking=True. The MTP head was retrained on the fine-tuned model's own outputs and accepts 89.4% of drafted tokens on held-out rounds (the base model's head: 89.0%).

Results

Phone tasks

The Orvena bench has 547 held-out scenarios in 30 languages, none of which were used for training. They run through Orvena's own agent loop with the 4-bit model, on simulated phone data and MCP servers with the real services' tool lists. A scenario passes only when the right tools are called with the right arguments and the answer contains what it should, in the user's language. Orvena 4B and the base model run with thinking off. Apple's on-device model runs through the app's Apple Intelligence backend in the same loop; it supports 13 of the 30 languages, and the app only sends it requests in those. The scenarios, the tool catalog and every model's results are published as Orvena/orvena-bench.

	Orvena 4B	Base model	Apple on-device
All 547 scenarios	440 (80.4%)	345 (63.1%)	104 (19.0%)
In the 13 languages Apple's model supports (260)	220 (84.6%)	175 (67.3%)	77 (29.6%)
Everyday requests with connections installed (100)	83	60	23

The 13 languages are Danish, German, English, Spanish, French, Italian, Japanese, Korean, Dutch, Portuguese, Swedish, Turkish and Vietnamese.

Category	Scenarios	Orvena 4B	Base model	Apple on-device
Multi-step tasks	70	43	17	1
MCP connections	62	51	45	8
Places	38	35	26	12
Calendar	31	20	13	4
Web	31	29	26	15
Alarms and timers	25	20	17	5
No tool needed	23	16	19	6
Weather	22	18	18	7
Reminders	21	18	14	0
Recovering from tool errors	19	18	12	3
Travel times	19	19	17	1
Follow-up questions	18	13	9	0
Scheduled tasks	16	12	9	0
Things it can't do	13	9	10	6
Music	10	10	8	3
Health	7	7	6	3
Photos	7	6	6	3
Contacts	6	5	6	1
Files	5	4	3	0
Device	4	4	4	3

Multi-step tasks chain several tools in one request. "I've got that job interview tomorrow, set me an alarm for when I need to leave, I'm going on the tube" needs the calendar, the current location, the transit time and an alarm; "my notes from the flat viewing have the plumber's number in them somewhere, remind me tomorrow at 10 to call him" needs a file search before the reminder. That is where the fine-tune changed the most: 43 of 70 against 17.

The MCP scenarios by connection, Orvena 4B on two seeds (labels give seed 7 / seed 8). Over all 62, Orvena 4B passes 51 and 49, the base model 45 and Apple's on-device model 8.

Public benchmarks

Public tool-use benchmarks bring their own tools, formats and rules for when to call, ask or decline, and none of them were in Orvena 4B's training data. Where a call is clearly needed, Orvena 4B matches its base model, and when it does call, more of its nested call sequences are fully right. It more often calls a tool where it should ask for a missing detail or say it can't, and that is the main goal for the next version. Section 8 of the technical report has the full results for BFCL v4, NESTFUL, ToolSandbox, When2Call, MCPMark, IFEval, MGSM and MMLU.

On an iPhone

iPhone 17 Pro Max with the 4-bit MLX build in Orvena's agent loop: 14 tasks (tool chains, requests missing a detail, and requests it can't do), two rounds each, with the phone cooled between runs.

	Orvena 4B	Base model, thinking off	Base model, thinking auto
Median time per task	15.1 s	16.3 s	37.0 s
Tokens generated per turn	169	213	757

Thinking auto was Orvena's default before Orvena 4B. Decoding runs at about 21 tokens per second on this phone, and 23 tokens per second with the MTP head as a drafter (83% of drafted tokens accepted).

Using it

vLLM

vllm serve Orvena/Orvena-4B --max-model-len 32768 --language-model-only \
  --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_coder

With the MTP head for speculative decoding, add --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'. Drop --language-model-only to send images.

Tools go in the usual OpenAI tools field. To turn thinking on, send "chat_template_kwargs": {"enable_thinking": true}; the fine-tune was trained without it. generation_config.json sets the sampling Orvena uses, temperature 0.7 and top-p 0.8; runtimes that don't read it should be given these values.

Other runtimes

The weights keep the Qwen3.5 architecture and layout, so runtimes that support it, including Transformers and SGLang, run Orvena 4B as they are. For Apple silicon, use Orvena/Orvena-4B-MLX-4bit.