PRA Runtime Bundle for mlx-community/gemma-3-1b-it-4bit · MLX / 4bit

What this PRA Runtime Bundle is

This repository packages the model-specific Progressive Retrieval Attention (PRA) structural mapping, runtime profiles, optional learned components, compatibility metadata, and measured qualification evidence. It does not contain the base-model weights and is not an ordinary LoRA quality fine-tune.

Base model: mlx-community/gemma-3-1b-it-4bit
Immutable revision: 2d44e83dc9e80843d22fb941d3d699a0b1351aa6
Architecture: Gemma3ForCausalLM
Parameters: 1B
Tokenizer revision: 2d44e83dc9e80843d22fb941d3d699a0b1351aa6

Recommended configuration

Engine: mlx
Recommended PRA mode: Selected Context
Recommended profile: BALANCED
Bundle evidence tier: CONTROLLED
Native Memory status: AVAILABLE

Availability, qualification, and recommendation are separate. A mode may be implemented without being qualified or recommended for this identity.

Headline results

No paired end-task headline is available for this exact model, revision, quantization, engine, profile, and execution mode. Routing diagnostics below must not be interpreted as application quality.

Installation

pip install 'pra-hf[hf-hub,hf-runtime]'
pra doctor

Quickstart

pra inspect mlx-community/gemma-3-1b-it-4bit -e mlx -a EInnovator/pra-gemma3-1b-mlx-4bit
pra evaluate mlx-community/gemma-3-1b-it-4bit -e mlx -D qasper -a EInnovator/pra-gemma3-1b-mlx-4bit
pra recommend .pra/runs/latest
pra serve mlx-community/gemma-3-1b-it-4bit -e mlx -a EInnovator/pra-gemma3-1b-mlx-4bit -p balanced

Profiles

Profile	Purpose	Routing	Consumer layers	Status	Recommendation
QUALITY	Candidate maximum-quality profile; held-out calibration is incomplete	generic cosine	5, 11, 17, 23	CALIBRATION_PENDING	Not promoted
BALANCED	Qualified default preserving the all-eligible consumer geometry	generic cosine	5, 11, 17, 23	QUALIFIED	Default
ECONOMY	Reduced-consumer candidate; the held-out quality gate has not passed	generic cosine	CALIBRATION_PENDING	CALIBRATION_PENDING	Not promoted
QASPER-LEARNED	Research-only learned routing profile qualified only on matched QASPER routing diagnostics	combined-router-d128	5, 11, 17, 23	RESEARCH	Not promoted

Engine compatibility

Engine	Selected Context	Native Memory	Native Serving	Recommended today
mlx	validated	AVAILABLE	NOT_MEASURED	Selected Context with BALANCED
hf	portable	NOT_MEASURED for the full-precision HF counterpart	NOT_MEASURED	Selected Context; exact MLX artifact only

End-to-end qualification

What remains to be measured: paired end-task quality for this exact bundle identity.

Native Memory qualification

What remains to be measured: paired Selected Context versus Native Memory quality and serving economics.

Research diagnostics

Dataset	Router/profile	Metric	Value	Cohort	Evidence
qasper	balanced	R@20%	0.2259	16	CONTROLLED
qasper	qasper-learned	R@20%	0.4539	16	CONTROLLED
hotpotqa	balanced	R@20%	0.3365	16	CONTROLLED
hotpotqa	qasper-learned	R@20%	0.318	16	CONTROLLED
combined	balanced	R@20%	0.2812	32	CONTROLLED
combined	qasper-learned	R@20%	0.3859	32	CONTROLLED

These are qualification measurements, not guaranteed production performance. Run pra evaluate on your hardware and workload. Engine version, profile, cohort, evidence tier, date, and artifact provenance remain recorded in qualification/ and bundle.yaml.

How to evaluate locally

pra evaluate mlx-community/gemma-3-1b-it-4bit -e mlx -a EInnovator/pra-gemma3-1b-mlx-4bit -D qasper -o .pra/runs/qasper
pra recommend .pra/runs/qasper
pra report .pra/runs/qasper --format html

Known limitations

The learned router improves QASPER but is not uniformly positive on HotpotQA; it is opt-in rather than the bundle default.
Paired natural-QA evidence contains five examples per dataset and supports engine qualification, not production qualification.
Reduced consumer-layer configurations failed the held-out quality gate; BALANCED therefore retains all eligible layers.
The qualification identity is the exact 4-bit MLX model and revision; it does not transfer automatically to full-precision Hugging Face weights or another quantization.
Base-model and dataset licenses apply separately to the router artifact.