Views
No views yet
[!TIP] KV-cache quantization (upstream, no fork needed): llama.cpp/Ollama cover this natively —-ctk q8_0 -ctv q8_0(~half KV memory, negligible quality loss) or-ctk q4_0 -ctv q4_0(~quarter memory, small quality cost). In Ollama:OLLAMA_KV_CACHE_TYPE=q8_0withOLLAMA_FLASH_ATTENTION=1.
nvidia/Nemotron-Cascade-2-30B-A3B quantized pack, published as Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-IQ4_XS.pipeline_tag: text-generation.
This is a Mixture-of-Experts (MoE) model — a subset of experts is active per token; total and active parameter counts differ.
This is a llama.cpp GGUF conversion of the text tower; no modality beyond pipeline_tag above is claimed or included.nvidia/Nemotron-Cascade-2-30B-A3B; all credit for the original model, training, and weights belongs to the upstream authors. This repo republishes a quantized conversion of those weights only.