# Is Orvena 4B SOTA?

Pending benchmarks. Announced Nov 4, 2026; no independent results yet.

As of Nov 22, 2026, Orvena 4B is pending benchmarks on isitsota: announced Nov 4, 2026, with no independent results on the boards we track yet.

Orvena's open-weight on-device assistant model for the Orvena iPhone app: a LoRA fine-tune of Qwen3.5-4B (LoRA r=16, alpha 320 on all 248 linear layers, merged) that keeps the base architecture, including the vision encoder, and answers without a separate thinking step by default. Trained for phone tools (calendar, alarms, places, travel times, web) and MCP connections such as Notion, Todoist, Airtable and Gmail, in 30 languages. Apache-2.0 bf16 weights with a retrained MTP head, plus a 4-bit MLX build the app downloads. No hosted API stated.

Canonical: https://isitsota.com/m/orvena-4b
Last updated: 2026-11-05
Tracking since: 2026-11-05

## Announced facts

| Fact | Value |
| --- | --- |
| Lab | Orvena |
| Announced | Nov 4, 2026 |
| API | Not yet · No hosted API stated; vLLM / Transformers / SGLang instructions for local serving |
| Open weights | Published |
| Parameters | 4B (Qwen3.5-4B backbone) |
| Base model | Qwen/Qwen3.5-4B (Alibaba); 24 Gated DeltaNet layers, 8 full-attention layers, vision encoder retained |
| Training | LoRA r=16, alpha 320 on all 248 language-model linear layers for one epoch, then merged; thinking off; MTP head retrained on the fine-tuned model's outputs |
| Training data | 3,397 simulated-iPhone scenarios (11,161 rounds) with Orvena's tool catalog and MCP tool lists from 12 services, plus no-tool/restraint sets and 600 IFEval-style instruction-following rows |
| App | Default model in Orvena 2.5 for iPhone; 4-bit MLX build is what the app downloads |
| Languages | 30 languages listed on the model card |
| Checkpoints | Orvena/Orvena-4B (bf16 + MTP) and Orvena/Orvena-4B-MLX-4bit on Hugging Face; technical report PDF on the card |
| License | Apache-2.0 |

Tags marked unsure are not stated on the lab's own pages.

## What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

- [x] Publicly announced with a source
- [x] Usable by the public (API or weights)
- [ ] Listed on an independent board we track
- [ ] Enough results for a rank in a category
- [ ] Holds across two snapshots (crowns only)

## What the lab claims

Self-reported. Shown for context; not used in any verdict.

- Lab claim: on the Orvena bench of 547 held-out scenarios, Orvena 4B passed 440 (80.4%), against 345 (63.1%) for Qwen3.5-4B and 104 (19.0%) for Apple's on-device model.
- Lab claim: on multi-step tasks, 43 of 70 against 17 for the base model.
- Lab claim: on an iPhone 17 Pro Max with the 4-bit MLX build, median time per task was 15.1 s (base thinking off: 16.3 s; thinking auto: 37.0 s).

## Sources

- REPO: [Orvena/Orvena-4B model card (Hugging Face)](https://huggingface.co/Orvena/Orvena-4B)
- REPO: [Orvena/Orvena-4B-MLX-4bit model card (Hugging Face)](https://huggingface.co/Orvena/Orvena-4B-MLX-4bit)
- LAB: [Orvena announcement on X](https://x.com/orvenaAI/status/2118321172420960536) (2026-11-05)
- LAB: [Orvena app site](https://orvena.app)

Tracking continues until an independent board lists it.

## Related

- Lab: [Orvena](https://isitsota.com/labs/orvena.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/orvena-4b
