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 about 19 hours ago
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp updated a model 3 days ago
satgeze/GLM-5.3-Flash-EXL3-TR3-3.5bpw published a model 3 days ago
satgeze/GLM-5.3-Flash-EXL3-TR3-3.5bpwOrganizations
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 • 2.62k • 7 -
satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 12B • Updated • 2.43k • 5 -
satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 25B • Updated • 2.13k • 5 -
satgeze/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 31B • Updated • 4.79k • 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 • 2.62k • 7 -
satgeze/Gemma4-12B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 12B • Updated • 2.43k • 5 -
satgeze/Gemma4-26B-A4B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 25B • Updated • 2.13k • 5 -
satgeze/Gemma4-31B-Uncensored-HauhauCS-1M-GGUF
Text Generation • 31B • Updated • 4.79k • 2
Ornith-1.0 with YaRN 1M context, needle-certified, MTP speculative decoding and vision. Full quant ladders on ModelScope.