<!-- agent-source-envelope -->
# Artifact: Hugging Face Specialist Model Archive v1 | PTLLM

> The local specialist model cache was promoted to Hugging Face or deleted when safely re-downloadable from upstream repos.

Canonical: https://posttrainllm.com/artifacts/hf-specialist-model-archive-v1
<!-- /agent-source-envelope -->

Artifact storage cleanup

Report artifact

2026-07-03

This archive makes artifact storage explicit: unique posttrainllm model outputs live on Hugging Face, while plain upstream base-model caches are removed locally instead of being mirrored under posttrainllm.

Hugging Face, artifacts, specialists, cleanup

## Headline Numbers

Evidence class applies to each value: measured = retained evaluation or
runtime result; historical = recorded result not freshly reproduced;
derived = calculated or decided from records; observed = current artifact
state; not-measured = an explicit evidence gap.

**posttrainllm HF repos:** 6

all have first-class case studies

Evidence: observed

**Local model cache:** cleared

after upload/remote-size verification

Evidence: observed

**Storage policy:** HF first

R2 remains optional private cache or legacy mirror

Evidence: derived

## Competitive Context

| System | Metric | Score | Size / Class | Comparable? | Readout |
| --- | --- | --- | --- | --- | --- |
| [Hugging Face artifact storage](https://huggingface.co/posttrainllm) | public model distribution | active | model repos | Direct | Current target for public weights, adapters, and large specialist artifacts. |
| Local Mac cache | durable artifact storage | rejected | ~30GB cleaned | Direct | Useful during training, but not the system of record after a model is uploaded or known re-downloadable. |
| Cloudflare R2 | artifact storage role | optional | private cache / legacy mirror | Directional | No longer the default public artifact store for model weights. |

Direct rows share this artifact's eval setup. Directional rows are
useful market context but should not be read as leaderboard claims.

## Uploaded posttrainllm artifacts

| Artifact | HF repo | Status | Readout |
| --- | --- | --- | --- |
| pace-intent-router-v8 | pace-intent-router-v8 | release-ready / rejected winner | 57.1% sealed accuracy at 3.8ms mean; source-matched 95.5% did not generalize |
| mt4b_fused | qwen3-4b-file-ops-distilled | release-ready | File-ops hard gate 58% -> 100%; breadth regression disclosed |
| mt4b_rest_fused | qwen3-4b-rest-fused | routed specialist | Fresh 12/12 vs 9/12 depth win; 25/45 vs 30/45 breadth reject |
| mt4b_mb_fused | qwen3-4b-multibackend-distilled | archive / failed attempt | Negative-transfer comparison artifact: depth 100%, breadth 31% |
| vibethinker-3b-mlx | vibethinker-3b-mlx | archive | Local MLX conversion of the VibeThinker 3B reasoning specialist |
| vibe_distill_fused | vibethinker-3b-agentic-distilled | archive | posttrainllm distilled VibeThinker variant; needs eval promotion before product use |

## Deleted upstream caches

| Local cache | Upstream repo | Reason |
| --- | --- | --- |
| mxbai-embed-large-v1 | mixedbread-ai/mxbai-embed-large-v1 | Public upstream cache; no posttrainllm delta |
| qwen3-embedding-0.6b | Qwen/Qwen3-Embedding-0.6B | Public upstream cache; no posttrainllm delta |
| qwen3-vl-2b-instruct | Qwen/Qwen3-VL-2B-Instruct | Public upstream cache; no posttrainllm delta |

## Release Blockers

### Archive entries are not ship decisions

Public weights can be useful as evidence without being the selected model for Pace or any product lane.

**Unblock:** Promote only candidates with a current factory run, eval report, package metadata, and routed-use decision.

### VibeThinker distilled eval needs promotion

The weights are preserved, but the public artifact should not imply a measured win until the eval evidence is attached.

**Unblock:** Run the factory eval gate and publish a before/after report before using it as a specialist package.

## Evidence

- [Pace router HF model](https://huggingface.co/posttrainllm/pace-intent-router-v8)

- [File-ops HF model](https://huggingface.co/posttrainllm/qwen3-4b-file-ops-distilled)

- [ReST HF model](https://huggingface.co/posttrainllm/qwen3-4b-rest-fused)

- [Multibackend HF model](https://huggingface.co/posttrainllm/qwen3-4b-multibackend-distilled)

- [VibeThinker MLX HF model](https://huggingface.co/posttrainllm/vibethinker-3b-mlx)

- [VibeThinker distilled HF model](https://huggingface.co/posttrainllm/vibethinker-3b-agentic-distilled)

- [HF storage policy](https://posttrainllm.com/docs/factory/huggingface-artifact-storage)

- [Public artifacts policy](https://posttrainllm.com/docs/factory/public-artifacts)

## Next Release Action

Use this as the storage index; use the six dedicated model case studies for quality and decision evidence.
