mudler / KAT-Coder-V2.5-Dev-APEX-GGUF

huggingface.co
Total runs: 1.1M
24-hour runs: 0
7-day runs: -97.3K
30-day runs: -160.6K
Model's Last Updated: August 17 2026

Introduction of KAT-Coder-V2.5-Dev-APEX-GGUF

Model Details of KAT-Coder-V2.5-Dev-APEX-GGUF

⚡ Each donation = another big MoE quantized

I host 30+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory) — enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant.
If APEX quants are useful to you, your support directly funds those bigger runs.

🎉 Patreon (Monthly) | ☕ Buy Me a Coffee | ⭐ GitHub Sponsors

KAT-Coder-V2.5-Dev — APEX GGUF

APEX (Adaptive Precision for EXpert Models) quantizations of Kwaipilot/KAT-Coder-V2.5-Dev — Kwaipilot's Mixture-of-Experts model for agentic coding.

Brought to you by the LocalAI team | APEX Project | Technical Report

Available Files
File Profile Best For
KAT-Coder-V2.5-Dev-APEX-I-Balanced.gguf I-Balanced Best overall — imatrix-enhanced
KAT-Coder-V2.5-Dev-APEX-I-Quality.gguf I-Quality Highest quality with imatrix
KAT-Coder-V2.5-Dev-APEX-Quality.gguf Quality Highest quality (no imatrix)
KAT-Coder-V2.5-Dev-APEX-Balanced.gguf Balanced General purpose
KAT-Coder-V2.5-Dev-APEX-I-Compact.gguf I-Compact Consumer GPUs, imatrix-enhanced
KAT-Coder-V2.5-Dev-APEX-Compact.gguf Compact Consumer GPUs
KAT-Coder-V2.5-Dev-APEX-I-Mini.gguf I-Mini Smallest viable, fastest inference
What is APEX?

APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient — edge layers (first/last 5) get higher precision, middle layers compress more aggressively. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).

In MoE models the routed-expert FFN tensors dominate the weight budget but only ~8/256 experts activate per token, so APEX compresses middle-layer experts hardest while preserving edge layers, attention, and the always-active shared expert.

See the APEX project for full details.

Architecture
  • Model : KAT-Coder-V2.5-Dev (Qwen3_5MoeForConditionalGeneration)
  • Layers : 40 · Experts : 256 routed + 1 shared (8 active per token)
  • Attention : 16 heads / 2 KV, hybrid (full attention every 4th layer)
  • Calibration : v1.3 diverse dataset

Note: the config advertises an image token, but the released checkpoint ships no vision encoder weights, so these are text-only GGUFs (no mmproj).

Run with LocalAI
local-ai run mudler/KAT-Coder-V2.5-Dev-APEX-GGUF@KAT-Coder-V2.5-Dev-APEX-I-Balanced.gguf
Credits

APEX is brought to you by the LocalAI team. Built on llama.cpp . Base model by Kwaipilot .

Runs of mudler KAT-Coder-V2.5-Dev-APEX-GGUF on huggingface.co

1.1M
Total runs
0
24-hour runs
-19.3K
3-day runs
-97.3K
7-day runs
-160.6K
30-day runs

More Information About KAT-Coder-V2.5-Dev-APEX-GGUF huggingface.co Model

More KAT-Coder-V2.5-Dev-APEX-GGUF license Visit here:

https://choosealicense.com/licenses/apache-2.0

KAT-Coder-V2.5-Dev-APEX-GGUF huggingface.co

KAT-Coder-V2.5-Dev-APEX-GGUF huggingface.co is an AI model on huggingface.co that provides KAT-Coder-V2.5-Dev-APEX-GGUF's model effect (), which can be used instantly with this mudler KAT-Coder-V2.5-Dev-APEX-GGUF model. huggingface.co supports a free trial of the KAT-Coder-V2.5-Dev-APEX-GGUF model, and also provides paid use of the KAT-Coder-V2.5-Dev-APEX-GGUF. Support call KAT-Coder-V2.5-Dev-APEX-GGUF model through api, including Node.js, Python, http.

KAT-Coder-V2.5-Dev-APEX-GGUF huggingface.co Url

https://huggingface.co/mudler/KAT-Coder-V2.5-Dev-APEX-GGUF

mudler KAT-Coder-V2.5-Dev-APEX-GGUF online free

KAT-Coder-V2.5-Dev-APEX-GGUF huggingface.co is an online trial and call api platform, which integrates KAT-Coder-V2.5-Dev-APEX-GGUF's modeling effects, including api services, and provides a free online trial of KAT-Coder-V2.5-Dev-APEX-GGUF, you can try KAT-Coder-V2.5-Dev-APEX-GGUF online for free by clicking the link below.

mudler KAT-Coder-V2.5-Dev-APEX-GGUF online free url in huggingface.co:

https://huggingface.co/mudler/KAT-Coder-V2.5-Dev-APEX-GGUF

KAT-Coder-V2.5-Dev-APEX-GGUF install

KAT-Coder-V2.5-Dev-APEX-GGUF is an open source model from GitHub that offers a free installation service, and any user can find KAT-Coder-V2.5-Dev-APEX-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of KAT-Coder-V2.5-Dev-APEX-GGUF install, users can directly use KAT-Coder-V2.5-Dev-APEX-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

KAT-Coder-V2.5-Dev-APEX-GGUF install url in huggingface.co:

https://huggingface.co/mudler/KAT-Coder-V2.5-Dev-APEX-GGUF

Url of KAT-Coder-V2.5-Dev-APEX-GGUF

KAT-Coder-V2.5-Dev-APEX-GGUF huggingface.co Url

Provider of KAT-Coder-V2.5-Dev-APEX-GGUF huggingface.co

mudler
ORGANIZATIONS

Other API from mudler

huggingface.co

Total runs: 149.3K
Run Growth: -1.4M
Growth Rate: -910.17%
Updated:June 22 2026