minicpm5-stock-analyst-v2-mtp
A single 33M-parameter multi-token prediction head bolted onto a frozen MiniCPM5-1B, trained with self-distillation (FastMTP recipe) + a...
A single 33M-parameter multi-token prediction head bolted onto a frozen MiniCPM5-1B, trained with self-distillation (FastMTP recipe) + a...
GGUF conversion of z-lab/gemma4-12B-it-DFlash for use with llama.cpp. > This is a DFlash draft model, not a standalone...
kimi-k2.7-code-eagle3-mla is an Eagle3 MTP draft model with MLA (Multi-Latent Attention) for accelerating inference of Kimi-K2.7-Code under vLLM...
Эта черновая модель DFlash является совместной переподготовкой Z-Lab и Modal, обученной с длиной последовательности 40K и вниманием скользящего...
A Q80 GGUF of the Gemma 4 26B A4B (QAT) Multi-Token-Prediction «assistant» head, for use as a self-speculative...
GGUF conversion of Google’s google/gemma-4-12B-it-assistant draft / MTP assistant model for pairing with google/gemma-4-12B-it-compatible Gemma 4 12B instruction...
This is the official DFlare draft model checkpoint for Qwen/Qwen3-8B`**, released alongside the paper: > DFlare: Scaling Up...
Квантования GGUF z-лабораторной модели DFlash для Gemma 4 26B A4B. Используйте с BeeLlama.cpp, форком llama.cpp с расширенными функциями...
This model was converted to FP16 from z-lab/Qwen3.6-35B-A3B-DFlash BF16. >DFlash is a novel speculative decoding method that utilizes...
A DFlash draft model trained from Qwen3-32B using a EagleChat subset (English 200K + Chinese 200K) to accelerate...