GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

gbuzhf/KAT-Coder-V2.5-Dev-REAP-205E-MTP-GGUF overview

Withdrawn — KAT Coder V2.5 Dev REAP 205E MTP GGUF These artifacts were removed on 2026 09 12. The repository is kept only so the DOI continues to resolve. What…

retiredggufdoi:10.57967/hf/9938license:mitregion:us
Downloads
1,488
Likes
0
Pipeline
—
Author

Repository Files & Downloads

0 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Browse files on Hugging Face

Model Details

Model IDgbuzhf/KAT-Coder-V2.5-Dev-REAP-205E-MTP-GGUF
Authorgbuzhf
Pipeline—
Licensemit
Base model—
Last modified2026-09-12T02:15:46.000Z

Model README

---

license: mit

tags:

- retired

- gguf

---

Withdrawn — KAT-Coder-V2.5-Dev REAP-205E MTP GGUF

**These artifacts were removed on 2026-09-12. The repository is kept only so the DOI

continues to resolve.**

What was here

An expert-pruned build of Kwaipilot/KAT-Coder-V2.5-Dev published 2026-08-10:

256 → 205 experts per layer (19.92% pruned) by REAP saliency, with an MTP head grafted,

a BF16 master and nine quantized tiers.

Why it was withdrawn

A publication gate was skipped. The build procedure made draft-acceptance

measurement a hard stop — publish only above ~0.80 — and that measurement was never

run. No acceptance figure for this pruned model exists. The model card cited the

unpruned model's 0.90–0.94, which reads as validation of something that was never

tested. A separate open defect (wrong-language output) was also never closed.

Re-verification in 2026-08-15 confirmed the methodology was sound: the keep-index is

bit-exact REAP top-205/layer across all 40 layers, every rate-table number reproduces,

the GGUF structure passes all checks, and recipe parity against the unpruned release is

exact — 753 tensors, zero name or quant-type differences. **The pruning was done

correctly; the resulting model was never shown to work.** Those are different claims,

and only the first one was ever supported.

Withdrawing is the honest resolution. The alternative — leaving weights online whose

headline capability claim was borrowed from a different model — is worse than removing

them.

Where to go instead

| you want | go to |

|---|---|

| the unpruned model, same recipes, measured | gbuzhf/KAT-Coder-V2.5-Dev-MTP-GGUF |

| the upstream model | Kwaipilot/KAT-Coder-V2.5-Dev |

If you want to reproduce the pruning

The method is reproducible without these files. The saliency measurement and keep-index

derivation are documented, and the pruning itself is deterministic given the saliency

tensor. Anyone repeating it should run the acceptance gate that this release did not.

Citation

The DOI below still resolves to this page. It refers to the 2026-08-10 release, whose

files are no longer distributed and whose capability claims should not be cited.

Run gbuzhf/KAT-Coder-V2.5-Dev-REAP-205E-MTP-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models