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 1 day ago
MiniMaxAI/MiniMax-H3 liked a model 2 days ago
antirez/deepseek-v4-gguf liked a model 3 days ago
baidu/Unlimited-OCROrganizations
None yet
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 • 8.72k • 4 -
satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 12B • Updated • 11.1k • 3 -
satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 25B • Updated • 6.95k • 4 -
satgeze/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 31B • Updated • 3.62k • 2
DSpark drafter heads for llama.cpp (measured speedups) and the self-distillation datasets behind them.
Models needle-certified past one million tokens, plus the ceiling studies. All raw data published, misses included.
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 • 8.72k • 4 -
satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 12B • Updated • 11.1k • 3 -
satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 25B • Updated • 6.95k • 4 -
satgeze/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 31B • Updated • 3.62k • 2
Ornith-1.0 with YaRN 1M context, needle-certified, MTP speculative decoding and vision. Full quant ladders on ModelScope.