DFlash: Block Diffusion for Flash Speculative Decoding
Paper • 2602.06036 • Published • 81
DFlash
Block Diffusion for Flash Speculative Decoding
-
-
z-lab/gemma-4-31B-it-DFlash
Text Generation • 2B • Updated • 32.4k • 91 -
z-lab/gemma-4-26B-A4B-it-DFlash
Text Generation • 0.4B • Updated • 13.9k • 46 -
z-lab/MiniMax-M2.7-DFlash
0.6B • Updated • 267 • 18 -
z-lab/MiniMax-M2.5-DFlash
2B • Updated • 58 • 7 -
z-lab/Kimi-K2.6-DFlash
Text Generation • 3B • Updated • 69 • 9 -
z-lab/Kimi-K2.5-DFlash
Text Generation • 3B • Updated • 5.89k • 30 -
z-lab/Qwen3.6-27B-DFlash
Text Generation • 2B • Updated • 74.1k • 321 -
z-lab/Qwen3.6-35B-A3B-DFlash
Text Generation • 0.5B • Updated • 58.6k • 225 -
z-lab/Qwen3.5-4B-DFlash
Text Generation • 0.5B • Updated • 20.4k • 23 -
z-lab/Qwen3.5-9B-DFlash
Text Generation • 1B • Updated • 17.7k • 32 -
z-lab/Qwen3.5-27B-DFlash
Text Generation • 2B • Updated • 7.42k • 109 -
z-lab/Qwen3.5-35B-A3B-DFlash
Text Generation • 0.5B • Updated • 5.73k • 36 -
z-lab/Qwen3.5-122B-A10B-DFlash
Text Generation • 0.5B • Updated • 9.79k • 15 -
z-lab/gpt-oss-20b-DFlash
Text Generation • 0.8B • Updated • 1.75k • 22 -
z-lab/gpt-oss-120b-DFlash
Text Generation • 0.8B • Updated • 3.72k • 11 -
z-lab/Qwen3-Coder-Next-DFlash
Text Generation • 0.5B • Updated • 2.62k • 11 -
z-lab/Qwen3-4B-DFlash-b16
Text Generation • 0.5B • Updated • 43.4k • 26 -
z-lab/Qwen3-8B-DFlash-b16
Text Generation • 1B • Updated • 53.1k • 24 -
z-lab/Qwen3-Coder-30B-A3B-DFlash
Text Generation • 0.5B • Updated • 6.6k • 30 -
z-lab/LLaMA3.1-8B-Instruct-DFlash-UltraChat
Text Generation • 1B • Updated • 17.2k • 3