pfeifferj/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Correct quantization bit metadata

Add quantized embedding shard

Clean up diagrams

Clarify MMLU-Pro protocol and simplify the model summary

Refresh checksums for Hub-generated LFS tracking

Update evaluation results and reproduction tools

Update README for split embeddings and simplify manifest

Separate BF16 n-gram and token embeddings from the main GGUF

Add a practical TL;DR at the top of the model card

Refresh README checksum

Add DOI to the release citation

GSQ-RCO GGUF release: weights, card, evidence

initial commit