10 results

dflash2

inall models datasets apps agents people projects

Models

All models matching “dflash2”

z-lab /Qwen3.8-27B-DFlash2-GGUFtext-generationllama.cpp136 likes706k downloads28d agoHugging Face incoai /Qwen3.8-27B-DFlash2text-generationtransformers248 likes383k downloads4d agoHugging Face z-lab /Qwen3.8-27B-DFlash2text-generationtransformers288 likes363k downloads1mo agoHugging Face nerkyor /Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUFiq77 likes83k downloads13d agoHugging Face incoai /Qwen3.8-27B-DFlash2-GGUFtext-generationllama.cpp158 likes65k downloads24d agoHugging Face nerkyor /Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2text-generationiq40 likes48k downloads10d agoHugging Face incoai /GLM-5.3-Flash-DFlash2text-generationtransformers115 likes45k downloads22d agoHugging Face syvai /Qwen3.8-27B-DFlash2-W4A1617 likes12k downloads1mo agoHugging Face

Datasets

All datasets matching “dflash2”

hamiejuice /qwen3.8-27b-uncensored-dflash2-m4-pro-benchmark Qwen3.8-27B (MLX 4-bit) + DFlash2 speculative decoding on M4 Pro — benchmark recipe This is a benchmark recipe, not redistributed weights. It records the exact hardware, software, and commands used to measure a 2.06x generation-throughput speedup with DFlash speculative decoding, and how to rerun it. Result HumanEval, 20 samples, max 256 new tokens, temperature 0 (greedy), reasoning off, block size 5, paired baseline and DFlash under identical settings. Other… See the full description on the dataset page: https://huggingface.co/datasets/hamiejuice/qwen3.8-27b-uncensored-dflash2-m4-pro-benchmark.textn<1K0 likes51 downloads22d agoHugging Face ggggggggg2 /llama-cpp-dflash2-cuda-bin0 likes33 downloads28d agoHugging Face