You can deploy this model and start earning money today!

tuxevil/
home-assistant-specialist-v0.4-4b-gguf-q5

Name: home-assistant-specialist-v0.4-4b-gguf-q5
Availability: InStock

Views

No views yet

Home Assistant Specialist v0.4 — Qwen3-4B Q5_K_M

GGUF artifact for local Ollama inference.

File: Qwen3-4B-Instruct-2507.Q5_K_M.gguf Quantization: Q5_K_M Task: strict ha-action-v3 Home Assistant JSON planning. Dataset provenance: V4 combines validated rows from acon96/Home-Assistant-Requests, acon96/Home-Assistant-Requests-V2, and project-curated contract cases. See the V4 dataset card for counts and filtering details.

Benchmark

Best observed Qwen3-4B Ollama quantization in this run.

Metric	Result
Exact match	95.68%
Safety OK	96.64%
Entity not invented	100.00%
Mean latency	1.162 s

The evaluation uses the fixed 417-case test split from tuxevil/Home-Assistant-Requests-V4.

Same-quantization model comparison

Quantization	Qwen3-8B exact	Qwen3-4B exact	Delta	Qwen3-8B safety	Qwen3-4B safety	Delta
Q4_K_M	91.85%	87.53%	+4.32 pp	93.05%	88.49%	+4.56 pp
Q5_K_M	97.36%	95.68%	+1.68 pp	98.32%	96.64%	+1.68 pp
Q6_K	97.36%	92.81%	+4.55 pp	98.32%	94.48%	+3.84 pp
Q8_0	Not published	92.57%	—	Not published	93.76%	—

Hugging Face / Transformers reference

Model	Base 4-bit exact	Adapter 4-bit exact	Merged FP16 exact	Base safety	Adapter safety	Merged FP16 safety
Qwen3-8B	0.00%	99.28%	99.20%*	84.17%	100.00%	99.50%*
Qwen3-4B	0.00%	98.08%	88.25%	75.54%	98.80%	89.69%

* Qwen3-8B FP16 published reference retains exact-match and safety metrics; other FP16 fields were not retained in the artifact manifest.

Quantization comparison

Quantization	Exact match	Safety OK	Mean latency	Deployment note
Q4_K_M	87.53%	88.49%	1.096 s	Lowest quality
Q5_K_M	95.68%	96.64%	1.162 s	Best observed
Q6_K	92.81%	94.48%	1.234 s	No quality gain over Q5
Q8_0	92.57%	93.76%	1.171 s	Below Q5 in this run

Ollama

The repository includes a Modelfile. Example:

ollama create home-assistant-specialist-v0.4-4b-q5 -f Modelfile

Use the exact model tag and verify the runtime with the full held-out benchmark before production use.

Safety

Do not execute generated JSON directly. Enforce status, service, entity, and parameter allowlists against live Home Assistant context.

tuxevil/home-assistant-specialist-v0.4-4b-gguf-q5