Ornith-1.0-35B-Heretic-MTP
HERETIC 1.4.0MTPAPEXMIT Ornith-1.0-35B-Heretic-MTP-APEX English | 📖 中文文档 Heretic Trial 63 BF16 merge · compatible MTP head · APEX...
HERETIC 1.4.0MTPAPEXMIT Ornith-1.0-35B-Heretic-MTP-APEX English | 📖 中文文档 Heretic Trial 63 BF16 merge · compatible MTP head · APEX...
This repository contains a 4-bit RTN-quantized version of the Tencent Hy3 Mixture-of-Experts model. Hy3 is a 295B-parameter MoE...
Official llama.cpp prebuilt binaries without this compatibility patch will fail to load this GGUF. Reason: unpatched official llama.cpp...
We reduce Qwen3.5-4B inference latency on a single A10G by quantizing both the target model and its speculative-decoding...
A load-and-go FP8 quantization of google/gemma-4-12B-it, plus a reproducible recipe for running it with DeepSeek DSpark speculative decoding...
MLX format quantization of deepreinforce-ai/Ornith-1.0-35B, produced with mlx-optiq. This repository also ships a grafted Multi-Token Prediction (MTP) head...
> TL;DR: 12,63 ГБ MLX-квант Qwen3,6-35B-A3B. На 16,8% меньше, чем у населения > TurboQuant-3bit MLX-квант при статистически связанной...
This repo contains three experimental IQ1M` GGUF quants derived from REAP-pruned Qwen 3.6 35B A3B checkpoints. I just...
Quant generated from: https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2 The original GGUF quants provided by Orenguteng (https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF) did not include a Q6_K, thus...
Pearl-certified variant of Llama-3.3-70B-Instruct, intended to run with the Pearl vLLM mining plugin. — Project website: https://pearlresearch.ai —...