Groot-19B-A3B-TTQ-GGUF
TTQ (TokenTinkerer Quant) is an eleven-rung GGUF ladder for GrootTeam/Groot-19B-A3B-261023, from 3.56 bpw to 8.50 bpw (7.88 →...
TTQ (TokenTinkerer Quant) is an eleven-rung GGUF ladder for GrootTeam/Groot-19B-A3B-261023, from 3.56 bpw to 8.50 bpw (7.88 →...
The only Ornith MTP build that fits 24 GB cards. Ornith-1.0-35B (Q4KM) with the multi-token-prediction head from Qwen3.6-35B-A3B-MTP...
MLX format quantization of deepreinforce-ai/Ornith-1.0-35B, produced with mlx-optiq. This repository also ships a grafted Multi-Token Prediction (MTP) head...
RTX 5090 Windows native GGUF comparison — updated July 19, 2026 Native llama.cpp conversions of NVIDIA and Unsloth...
калиброванный imatrix IQ3_XXS для nex-agi/Nex-N2-mini. 13,6 ГБ на диске, помещается в 15 ГБ памяти графического процессора с местом для контекста....