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
updated a dataset about 10 hours ago
satgeze/Qwen3.5-0.8B-selfdistill updated a model about 10 hours ago
satgeze/Qwen3.5-0.8B-DSpark liked a model 1 day ago
Kuberwastaken/Kimi-K3-GGUFOrganizations
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 • 7.7k • 4 -
satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 12B • Updated • 10k • 3 -
satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 25B • Updated • 5.53k • 2 -
satgeze/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 31B • Updated • 3.4k • 1
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 • 7.7k • 4 -
satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 12B • Updated • 10k • 3 -
satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 25B • Updated • 5.53k • 2 -
satgeze/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 31B • Updated • 3.4k • 1
Ornith-1.0 with YaRN 1M context, needle-certified, MTP speculative decoding and vision. Full quant ladders on ModelScope.