---

license: apache-2.0

base_model: Kwaipilot/KAT-Coder-V2.5-Dev

pipeline_tag: text-generation

library_name: gguf

tags:

- gguf

- moe

- apex

- quantized

- imatrix

- qwen3_5_moe

- coding

- llama.cpp

---

Moved → Myric/KAT-Coder-V2.5-Dev-MTP-APEX-GGUF

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.*