Selora
local model for Home Assistant
Details
- External ID
- 48576208
- Source
- HN
- Company
- —
- Product
- Selora
- Website domain
- github.com
- Launched
- June 17, 2026
- Cohort
- —
- Upvotes
- 7
- Upvotes percentile
- 0.42008196721311475
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
Selora AI Local is an open-source, Qwen-based model for Home Assistant.Specs: Qwen3 1.7B base model (Q6 quantized~1.6GB) Four Home Assistant-specific LoRA adapters: - Answers - Clarifications - Automations - Commands ~3.5 GB total download size Runs locally via llama.cppWe chose a Qwen-based architecture because of a paper on Arxiv (link below) which applied a Qwen based model for local LLM configuration, and showed promising results. We took it a step further in application by training LoRA adapters specialized in Home Assistant configuration.This alpha release ships our base model with four specialist LoRA adapters preloaded for faster response: answers, clarifications, automations, and commands. The Q6 quantized base model is 1.6GB and the adapters are less than 100MB running either on self-hosted llama.cpp, or on Selora Hub devices, where everything is preconfigured and plug-and-play for you.We started working on this because the existing options for local LLMs in Home Assistant lack knowledge to run anything useful, so users opt for very large LLMs, typically a cloud model that’s too expensive and not optimized for the kind of high-frequency, always-on smart home use we care about. We think there's a need for open-source models that are small and specialized enough to run on the kind of hardware people actually have at home.Would love any feedback, questions, or ideas. Thanks for checking it out!Hugging Face: https://huggingface.co/selorahomes/Selora-AI Arxiv: https://arxiv.org/abs/2502.12923 More details: https://selorahomes.com/selora-ai/
Enrichment
- Theme
- lightweight and on-device AI runtimes
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- local model for home assistant
- Manually corrected
- False
Could you build this?
No Developing custom domain-specific LoRA adapters across multiple agent tasks and packaging them with quantized base models requires deep ML fine-tuning expertise and domain datasets.
What it would actually take: The project requires curating extensive Home Assistant schema datasets, command corpora, and device interaction topologies, followed by fine-tuning multiple distinct LoRA adapters on a Qwen base model using PyTorch/Unsloth. The deployment stack relies on llama.cpp integration inside Home Assistant OS or Docker with strict latency constraints. Producing accurate function calling without hallucinations requires experienced ML fine-tuning engineering and deep knowledge of Home Assistant's internals.
Discussion
4 comments analyzed.
Competitors mentioned: Qwen8B
Concerns raised: No benchmark data or performance comparisons provided, Unclear pricing model for local version despite claiming it's free, Confusion between cloud and local model pricing/credits
Feature requests: Performance benchmarks against other models, Better documentation clarifying cloud vs local pricing
Competitors
Other products that read as similar to this one — 36 launches clear the similarity bar, closest 8 shown.
Attention rank: #25 of 37 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 209 days after the earliest competitor.
- HA-multilayered-LLM-Voice-Assistant-intent-local-cloud- · github · 2026-09-13 · 15 upvotes · similarity 0.42
- Qwen3.8-Max · ph · 2026-08-03 · 276 upvotes · similarity 0.39
- LocalLLM · hn · 2026-04-23 · 16 upvotes · similarity 0.39
- Tiny Aya · ph · 2026-04-05 · 211 upvotes · similarity 0.39
- First Claude Code client for Ollama local models · hn · 2026-01-22 · 44 upvotes · similarity 0.39
- qwenimage3.0-qwen-image-3.0-api · github · 2026-09-24 · 57 upvotes · similarity 0.37
- Gladys Assistant 5 · ph · 2026-09-29 · 89 upvotes · similarity 0.36
- Qwen 3.5 running on a $300 Android phone · hn · 2026-03-03 · 6 upvotes · similarity 0.36
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.