GGUF quantizations of DSpark speculative-decoding draft models (DFlash backbone + Markov head).
Ivan Neustroev
Anbeeld
AI & ML interests
Creator of BeeLlama.cpp
Recent Activity
updated a model about 21 hours ago
Anbeeld/Qwen3.8-27B-GGUF-Bartowski-SINQ published a model 1 day ago
Anbeeld/Qwen3.8-27B-GGUF-Bartowski-SINQ updated a model 4 days ago
Anbeeld/Qwen3.5-9B-GGUF-Bartowski-SINQOrganizations
None yet
GGUF DFlash 2 draft models with parallel block drafting and candidate path selection.
-
Anbeeld/GLM-5.3-DFlash2-GGUF
Text Generation • 2B • Updated • 2.82k • 1 -
Anbeeld/GLM-5.3-Flash-DFlash2-GGUF
Text Generation • 1B • Updated • 5.13k • 10 -
Anbeeld/Muse-Glimmer-30B-DFlash2-GGUF
Text Generation • 3B • Updated • 405 • 1 -
Anbeeld/Qwen3.8-27B-DFlash2-GGUF
Text Generation • 2B • Updated • 2.85k • 13
GGUF quantizations of DSpark speculative-decoding draft models (DFlash backbone + Markov head).
GGUF DFlash 2 draft models with parallel block drafting and candidate path selection.
-
Anbeeld/GLM-5.3-DFlash2-GGUF
Text Generation • 2B • Updated • 2.82k • 1 -
Anbeeld/GLM-5.3-Flash-DFlash2-GGUF
Text Generation • 1B • Updated • 5.13k • 10 -
Anbeeld/Muse-Glimmer-30B-DFlash2-GGUF
Text Generation • 3B • Updated • 405 • 1 -
Anbeeld/Qwen3.8-27B-DFlash2-GGUF
Text Generation • 2B • Updated • 2.85k • 13
GGUF DFlash draft models for speculative decoding, including Qwen, Kimi, Gemma, and MiniMax.