DSpark drafter heads for llama.cpp (measured speedups) and the self-distillation datasets behind them.
Sat Grewal PRO
satgeze
AI & ML interests
Optimise AI models for consumer grade systems resources
Recent Activity
liked a model 6 days ago
dealignai/MiMo-V2.6-Flash-RL-UNCENSORED liked a model 6 days ago
XiaomiMiMo/MiMo-V2.6-Flash-RL liked a model 7 days ago
Altworld/Hemmingway-1Organizations
None yet
Uncensored 1M Context: Gemma 4 + Qwen3.6
Uncensored trunks with YaRN 1M context, needle-certified, plus MTP speculative decoding and vision. Full archives on ModelScope.
-
satgeze/Qwen3.6-35B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 0.4B • Updated • 8.13k • 9 -
satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 12B • Updated • 2.35k • 7 -
satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 25B • Updated • 1.81k • 6 -
satgeze/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 31B • Updated • 1.07k • 3
DSpark speculative decoding
DSpark drafter heads for llama.cpp (measured speedups) and the self-distillation datasets behind them.
Beyond 1M Context
Models needle-certified past one million tokens, plus the ceiling studies. All raw data published, misses included.
Uncensored 1M Context: Gemma 4 + Qwen3.6
Uncensored trunks with YaRN 1M context, needle-certified, plus MTP speculative decoding and vision. Full archives on ModelScope.
-
satgeze/Qwen3.6-35B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 0.4B • Updated • 8.13k • 9 -
satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 12B • Updated • 2.35k • 7 -
satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 25B • Updated • 1.81k • 6 -
satgeze/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 31B • Updated • 1.07k • 3
Ornith 1M Context
Ornith-1.0 with YaRN 1M context, needle-certified, MTP speculative decoding and vision. Full quant ladders on ModelScope.