Qwen3.8-27B
This repository is a community conversion of Qwen/Qwen3.8-27B to the LiteRT-LM (.litertlm) format, made with litert-torch (commit 115a1360...
This repository is a community conversion of Qwen/Qwen3.8-27B to the LiteRT-LM (.litertlm) format, made with litert-torch (commit 115a1360...
A Blackfrost derisked derivative of NVIDIA Nemotron-3.5 Bolt 74B-A9B, built for professional cybersecurity work: false-refusal friction on legitimate...
A Blackfrost derisked derivative of NVIDIA Nemotron-3.5 Bolt 74B-A9B, built for professional cybersecurity work: false-refusal friction on legitimate...
HyLo converts a pretrained Transformer into a hybrid instead of pretraining one from scratch. Each layer is converted...
Speck2-140M-Instruct is a 140.7M parameter English instruction-tuned language model. It was initialized from Speck2-140M, a hybrid model pretrained...
Speck1.1-140M-Instruct is a 140.7M parameter English instruction-tuned language model. It was initialized from Speck1-140M, a hybrid model that...
Standard static quants (no imatrix) + APEX mixed-precision quants of SC117’s abliterix v6 trial 21 merge. Original model:...
Imatrix-guided, measured-allocation APEX quantizations of nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B — a Nemotron-H hybrid: 52 layers of which only 6 are full...
Rigel is a 2.3B-total, 360M-active-parameter hybrid Mamba-2 + attention mixture-of-experts base model, trained with LM Engine. It used...
LAMBA V1.0 is a ~177M-parameter language model trained from scratch on a Mamba-3 (SISO) + Grouped-Query Attention hybrid...