GLM-4.7-Flash-Eagle3
An EAGLE3 draft model that accelerates inference for zai-org/GLM-4.7-Flash (30B MoE, ~3B active) through speculative decoding. 1.66x mean...
An EAGLE3 draft model that accelerates inference for zai-org/GLM-4.7-Flash (30B MoE, ~3B active) through speculative decoding. 1.66x mean...
Эта модель представляет собой точно настроенную версию собственного модуля MTP DeepSeek-V3, оптимизированного для спекулятивного декодирования с использованием потерь...
Two quantizations of the DFlash 2 draft model for Qwen/Qwen3.8-27B, both calibrated with an importance matrix captured from...
This repository contains a DFlash draft model for moonshotai/Kimi-K3 trained only on a generic data mix (no tool...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
GGUF conversion of z-lab/Qwen3.6-35B-A3B-DFlash for llama.cpp. > This is a DFlash draft model, not a standalone language model....
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
Bielik-Minitron-7B-v3.0-DFlash is a DFlash draft model designed for use with Bielik-Minitron-7B-v3.0-Instruct. Its development and training were supported by...
I’ve been trying to get as much performance as possible out of a single DGX Spark with Gemma...
First public extraction of Google Gemma 4’s Multi-Token Prediction (MTP) drafter weights from LiteRT format into standard PyTorch...