Skip to content

Models and bundles

Picking a model on Katara means picking a bundle: a published description of exactly which weights, tokenizer, chat template, and runtime a provider must run. Every provider serving a bundle runs the same thing, so a request to katara/llama-3.1-8b-instruct@1 gets that model, whoever serves it.

Marketplaces without this rule end up with quietly different models behind one name. Katara’s validators send known prompts to every provider and score the answers against recorded results. That only works when the model is fixed.

It also keeps prices comparable. Providers compete on price and speed for the same bundle, not on what they secretly run.

Katara does. A new model means writing the bundle, pinning it on reference hardware, recording the validation prompts, and approving it. Providers then choose from the approved list. They cannot add their own.

Each approved bundle’s manifest is published at https://docs.katara.com/bundles/<bundle>.json, the address recorded on chain with its hash. Providers pass that file to the node. The current bundles:

  • llama-3.1-8b-instruct.v1.json: Llama 3.1 8B Instruct, 4-bit, Apple Silicon profile.

The @1 in a model id is the bundle version. A new version, for example one that adds a CUDA profile or changes quantisation, gets a new number. Old versions keep working until they are retired.

Some catalog entries are served only by the managed fallback, for example katara/deepseek-chat@1. No provider runs them. They exist so you can use a hosted model at a published price through the same API and wallet.