Mudler

Model

Laguna-XS-2.1-APEX-GGUF

Mudler

APEX (Adaptive Precision for EXpert Models) quantizations of poolside/Laguna-XS-2.1 — poolside's Laguna XS.2 Mixture-of-Experts model for coding and agentic software engineering. Brought to you by is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention, dense FFN) and applies a layer-wise precision gradient — edge layers 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 fire per token, so APEX…

Model

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

Mudler

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 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…

Model · Audio classification

ced-gguf

Mudler

GGUF quantizations of the CED family (Consistent Ensemble Distillation, Xiaomi) - SOTA-tier audio-tagging models that classify everyday sounds (baby cry, footsteps, glass breaking, alarms, dog bark,...) into the 527-class AudioSet ontology. These files run with ced.cpp, a standalone C++/ggml port (no Python, no PyTorch at inference), and with LocalAI via the ced backend. Converted from the mispeech/ced- checkpoints (Apache-2.0). CED is a plain AST/DeiT Vision Transformer over a log-mel spectrogram; the port is numerically equal to the PyTorch reference. One self-contained GGUF per size + quant (config, 527 labels, and the mel filterbank/window are all embedded). Pick by your accuracy/size…

Model · Object detection

locate-anything.cpp-gguf

Mudler

GGUF builds of nvidia/LocateAnything-3B for locate-anything.cpp - a C++/ggml inference engine for open-vocabulary detection / visual grounding, no Python at inference time. Brought to you by the LocalAI team. The detections are the same as the official PyTorch implementation (the engine is parity-gated against it), and it runs faster - on CPU and GPU. The full-precision f32 GGUF (~15 GB) is reproducible from the HF weights with scripts/convertlocateanythingtogguf.py in the repo. Same detections as the official model, faster. Full methodology, the warm/median setup, parity checks, and more images are in the repo's Slow-mode inference on the 448 fixture; vs official divides the official…