⚡ 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 **APEX (Adaptive Precision for EXpert Models)** quantizations of Kwaipilot/KAT-Coder-V2.5-Dev — Kwaipilot's Mixture-of-Experts model for agentic coding.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
⚡ 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 **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.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
分類準備中
入力 未確認→ 出力 未確認
Perplexity is measured on wikitext-2-raw. KL divergence is measured against the BF16 model on the same text. HellaSwag and Winogrande use 400 tasks each, zero-shot. The LiquidAI rows are the quantizations published by LiquidAI, measured the same way. Perplexity differences of about 0.2 are close to the measurement error (+/- 0.14). 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 get higher precision, middle layers get more aggressive compression. The I-variants use imatrix-guided quantization. APEX is brought to you by the LocalAI team. Developed through human-driven, AI-assisted research. Built on llama.cpp.
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
分類準備中
入力 未確認→ 出力 未確認
**locate-anything.cpp** 用の `nvidia/LocateAnything-3B` の GGUF ビルド - オープンボキャブラリー検出/ビジュアルグラウンディング向けの C++/ggml 推論エンジンで、推論時には Python を使用しません。検出結果は公式 PyTorch 実装と同じであり(エンジンはそれと同等性が保証されています)、CPU および GPU 上でより高速に動作します。フル精度の `f32` GGUF(約 15 GB)は、リポジトリ内の `scripts/convert_locateanything_to_gguf.py` を使用して HF 重みから再現可能です。
入力 画像→ 出力 テキスト
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
入力 テキスト→ 出力 音声
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
分類準備中
入力 未確認→ 出力 未確認
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
分類準備中
入力 未確認→ 出力 未確認
⚡ Each donation = another big MoE quantized I host 25+ 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. Benchmarks coming soon. For reference APEX benchmarks on the Qwen3.5-35B-A3B architecture, see mudler/Qwen3.5-35B-A3B-APEX-GGUF. 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 get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
入力 音声→ 出力 テキスト
GGUF conversion of `OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5` for moss-tts.cpp: a C++17/ggml inference port of the OpenMOSS MOSS-TTS family that runs entirely on stock ggml with no Python, ONNX or torch at inference time. The non-matmul tensors (all `lc.*` heads and embeddings, every norm and bias) are kept in f32 in every quant; only the Qwen3 global and GPT-J local attention/FFN matmuls are quantized, so the CPU gather/head paths stay exact. This port is numerically verified against the reference PyTorch implementation: the language model matches to about 1e-5 with an exact greedy code sequence, and the MOSS-Audio-Tokenizer-v2 decode matches at about 115 dB SNR (bit-exact in f32). On CPU it runs roughly twice as fast per frame as the reference PyTorch at the same f32 precision.
翻訳待ち・原文を表示
入力 テキスト→ 出力 音声
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
分類準備中
入力 未確認→ 出力 未確認
⚡ Each donation = another big MoE quantized I host 25+ 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. **APEX (Adaptive Precision for EXpert Models)** quantizations of nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16. 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 get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
分類準備中
入力 未確認→ 出力 未確認
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
分類準備中
入力 未確認→ 出力 未確認
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
分類準備中
入力 未確認→ 出力 未確認
⚡ 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 APEX quantizations of ornith-ai/Ornith-1.5-35B-A3B.
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
⚡ 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 APEX quantizations of ornith-ai/Ornith-1.5-35B-A3B.
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
GGUF-format weights for parakeet.cpp, a C++/ggml port of NVIDIA NeMo Parakeet that matches the upstream PyTorch models on CPU. This single repo collects **every supported model × quantization** as a flat set of `.gguf` files — download just the one you need. **F16 is the recommended default** — same accuracy as F32, ~1.7× smaller, and typically the fastest on modern CPUs via ggml's F32×F16 matmul fast path. Source: nvidia/parakeet-tdt_ctc-110m · Hybrid TDT+CTC (FastConformer) · heads: TDT + CTC
翻訳待ち・原文を表示
入力 音声→ 出力 テキスト
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
基本情報を収録・詳細は順次追加
分類準備中
入力 未確認→ 出力 未確認
⚡ Each donation = another big MoE quantized I host 25+ 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. All measurements on 8xRTX PRO 6000 Blackwell (768 GB VRAM). Perplexity on wikitext-2-raw, context 512. Accuracy benchmarks via llama.cpp (400 tasks each). 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 get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).
翻訳待ち・原文を表示
分類準備中
入力 未確認→ 出力 未確認
⚡ Each donation = another big MoE quantized I host 25+ 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. **Brought to you by the LocalAI team** -- the creators of LocalAI the open-source AI engine that runs any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. APEX (Adaptive Precision for EXpert Models) is a **novel quantization technique** for Mixture-of-Experts language models. Unlike uniform quantization methods that apply the same precision to every tensor, APEX introduces a **layer-wise precision gradient** combined with **MoE-aware tensor classification** and **diverse imatrix calibration** to achieve Q8_0-level quality at a fraction of the size. The method was discovered through systematic human-driven, AI-assisted research across 25+ quantization strategies. APEX outperforms Unsloth Dynamic 2.0 (UD) quantizations on accuracy benchmarks while being 2x smaller.
翻訳待ち・原文を表示
入力 テキスト→ 出力 テキスト
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
分類準備中
入力 未確認→ 出力 未確認