CyberNeurova-DeepSeek-V4-Flash-abliterated-v2-IQ3_XXS-AS-GGUF
> Tailor-made for the 128 GB M5 Max MacBook Pro. This quant was > designed, built, and benchmarked...
> Tailor-made for the 128 GB M5 Max MacBook Pro. This quant was > designed, built, and benchmarked...
A 2-bit quantization of deepseek-ai/DeepSeek-V4-Flash (299 B params, MoE) that serves on a single NVIDIA DGX Spark (GB10,...
REAP-pruned DeepSeek V4 Flash at K180 (180 routed experts per MoE layer, 30% pruning), with a hybrid mixed-precision...
Vipera-V4NM is a dynamically uncensored and abliterated version of deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct. This model was created using the Heretic framework,...
REAP-pruned DeepSeek V4 Flash at K128 (128 routed experts per MoE layer). Prunes 50% of routed experts via...
284B MoE · 13B Active · 61.6GB GGUF · CPU-Feasible Inference This section provides cryptographic verification of the...
Trained autonomously by the ml-intern Claude Code skill on a single RTX A6000. This is a ~130M-parameter down-scale...
🌟 Helio1-Ray-8B-Preview Agentic Reasoning & Code Model 8 миллиардов параметров. Агентский подход к решению задач. Программное мышление. >...
Эта модель представляет собой точно настроенную версию собственного модуля MTP DeepSeek-V3, оптимизированного для спекулятивного декодирования с использованием потерь...
Tobyworld Mirror Q4KM is a reflective, poetic AI model finetuned on the philosophy, lore, and cadence of the...