CoolFace
Modelpublic

philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-4bit

sourceHugging Faceapache-2.0updated 17d agoView on Hugging Face
5likes386downloads
11 commits on main
4e63f0417d ago

Clarify release scope and connect the model portfolio

philipjohnbasile
ecc13dd2mo ago

Replace single-sample throughput figures with characterised distributions: ranges, trial counts, methodology, and the 4-bit context-copy bimodality

philipjohnbasile
34a3f1a2mo ago

Withdraw incorrect throughput correction (measured under load); restore original figures, flagged unverified

philipjohnbasile
8031cb42mo ago

Correct throughput: republish measured AR/D1/D2/D3 and per-position acceptance

philipjohnbasile
1667a392mo ago

Correct behavioral claims and link validated v2 artifact

philipjohnbasile
b0af2e62mo ago

Credit nightmedia F32 source; add independent cosine validation

philipjohnbasile
81520832mo ago

Add LICENSE and NOTICE (Apache-2.0 compliance)

philipjohnbasile
1281abf2mo ago

Add LICENSE and NOTICE (Apache-2.0 compliance)

philipjohnbasile
2aed0da2mo ago

Correct per-variant draft acceptance (measured, identical prompt)

philipjohnbasile
bbaae7f2mo ago

Fable-Fusion-711 MLX conversion from Q8_0 MTP GGUF

philipjohnbasile
543cf072mo ago

initial commit

philipjohnbasile