The APEX quants of
Kwaipilot/KAT-Coder-V2.5-Dev
now live in a single repo:
→
Myric/KAT-Coder-V2.5-Dev-MTP-APEX-GGUF
|
file
|
size
|
|
KAT-Coder-V2.5-Dev-MTP-APEX-i-quality.gguf
|
20.72 GB
|
recommended —
includes a working MTP head
for speculative decoding
|
KAT-Coder-V2.5-Dev-APEX-dynamic.gguf
|
11.86 GiB
|
sized for a 16 GB card
|
kat-coder.imatrix
|
192 MB
|
the importance matrix, reusable for your own tiers
|
model-00014-of-mtp.safetensors
|
1.69 GB
|
the bf16 MTP head, if you want to redo the transplant
|
KAT-Coder ships
mtp_num_hidden_layers: 0
— no MTP head at all, so no speculative decoding is
possible out of the box, and that is true of the vendor release and of every other quant of this
model I am aware of. The build above transplants Qwen3.6-35B-A3B's own trained head onto it:
2.03× on a hard agentic-coding suite with correctness unchanged
(100% on both suites either
way — the head only drafts, the main model verifies).
This repo previously held only the imatrix, while its README described quants that were never
uploaded here. Everything is now in the repo linked above.