Public weights
YesHugging Face model repositoryobservedVibeThinker-3B Agentic Distilled
The experiment asked whether a reasoning-strong 3B base could become a better tool-calling student than Qwen3-4B. The fused weights were published, but the repository does not preserve a current before/after eval, regression review, or ship decision. This page is the honest case study of an unfinished proof: the artifact exists; the conclusion does not.
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.
Current agentic eval
Missingno promoted before/after resultnot-measuredReasoning retention
Unknownno post-distillation regression gatenot-measuredDecision
Inconclusiveweights are not a ship decisionderivedCompetitive Context
| System | Metric | Score | Size / Class | Comparable? | Readout |
|---|---|---|---|---|---|
| VibeThinker-3B agentic distilled | current tool-calling gate | not recorded | 3B | Direct | The intended candidate exists, but the required result is absent. |
| VibeThinker-3B MLX base | historical GSM8K sanity slice | 40/40 | 3B | Directional | Shows the source base's reasoning signal, not retained reasoning after agentic distillation. |
| Qwen3-4B ReST | recorded file-ops depth / breadth | 100% / 65% | 4B | Not comparable | The measured incumbent research candidate; no matched VibeThinker result exists. |
Direct rows share this artifact's eval setup. Directional rows are useful market context but should not be read as leaderboard claims.
Evidence audit
| Required case-study element | State | What can be said |
|---|---|---|
| Base identity | Recorded | VibeThinker-3B MLX reasoning base |
| Distilled fused weights | Public | Artifact is preserved |
| Frozen baseline | Missing | No before number |
| Current candidate eval | Missing | No after number |
| Breadth/reasoning regression | Missing | Retention unknown |
| Ship decision | Absent | Inconclusive archive only |
Release Blockers
No current before/after eval
Public weights alone cannot establish whether tool-calling improved or whether reasoning regressed.
Unblock: Freeze a matched baseline, agentic primary gate, and reasoning/breadth regression gate; then run both once under the same harness.
No specialist package or routing decision
The repository has no canonical package metadata that defines safe use or a ship/reject outcome.
Unblock: Only package after the frozen eval produces a defensible decision.