gemma-4-31B-it-UD-Q3_K_XL.gguf from unsloth/gemma-4-31B-it-GGUF (credit to the original model authors and quantizer), split into <2 GB shards with llama-gguf-split so it can be loaded by wllama in the browser.

Load the first shard; wllama resolves the rest automatically.