---
license: apache-2.0
tags:
  - flowcast
  - loudink
  - loudink-v1
  - voice-agent
  - mlx
  - apple-silicon
  - compact-ir
  - dictation
  - computer-use
library_name: mlx-lm
---

# flowcast-loudink-v1 (product: **loudink-v1** v0.4.0)

On-device dual-stack for **LoudInk / Flowcast** on Apple Silicon:

1. **Writer** — LFM2.5-1.2B LoRA (dictation polish / messages / email / prompts)
2. **Planner** — FunctionGemma compact-IR LoRA (computer-use plans)

Predecessor: [nsalerni/flowcast-v5-lite](https://huggingface.co/nsalerni/flowcast-v5-lite)

> **v1.1 track:** record-and-replay skills, richer real-world benches. This `0.4.0` freeze is the **loudink-v1** GA snapshot.

## Daily-Mac product bar (v0.4)

| Slice | Shipped | Neural | Latency |
|-------|---------|--------|---------|
| Writing (n=22) | **100%** | **86.4%** | p50 **181 ms** |
| Computer (n=34) | **100%** | — | mostly fast-path |
| Multi-step (n=21) | **100%** | — | mostly fast-path |
| **Overall (n=56)** | **100%** | — | — |
| IR honesty (n=112, no fast paths) | — | **46.4%** | — |

Also: user-demand writing honesty (v0.3 lineage) ~80% neural / 100% shipped with structural polish.

## Bundle layout

```
writer/                 # optional promoted_core_100.safetensors seed adapter
writer_unified/         # production writer LoRA (adapters.safetensors)
ir/                     # production IR LoRA (adapters.safetensors)
router.json
manifest.json
inference_config.json
```

**Bases are not vendored here** (size). Pull 4-bit bases from MLX community:

- Writer base: `mlx-community/LFM2.5-1.2B-Instruct-4bit`
- IR base: `mlx-community/functiongemma-270m-it-4bit`

Hot package class with both 4-bit bases: ~850 MiB primary / 900 MiB hard.

## Integration

```python
# pip install mlx-lm huggingface_hub
from huggingface_hub import snapshot_download

bundle = snapshot_download("nsalerni/flowcast-loudink-v1")
# runner_kind: loudink_v1
# polish_mode: structural
# writer_unified_adapter_path: {bundle}/writer_unified
# ir_adapter_path: {bundle}/ir
```

See `inference_config.json` and `client_contract.md` for Flowcast client fields.

## Methods (v0.4)

- Teacher SFT → RFT / expert iteration → **daily-mac RFT + residual micro gold**
- Structural polish (safety net; neural is promotion currency)
- IR honesty micro-SFT from transcript-first gold (sequence-aware)
- Transcript-first multi-step, Finder paths, Gmail compose, Shortcuts, web search

## License

Apache-2.0 (adapters). Base model licenses apply to the community 4-bit bases.