replace default model mistral:7b with qwen3:8b#915
Merged
Conversation
github-actions
bot
added
size/M
documentation
qwen3:8b supersedes mistral:7b as the recommended sub-14B open-source model with native tool use, thinking mode, and strong multilingual support at ~5 GB RAM footprint. - Update default model constant and config/default.toml - Replace all test fixtures and snapshot references - Add "qwen3"/"qwen" aliases to ChatTemplate::parse_str (maps to ChatML, which is the correct format for Qwen3) - Update --init wizard model suggestions and fallback defaults Closes #897
bug-ops
force-pushed
the
feat/qwen3-default-model
branch
from
cc284eb to
18865d0
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
mistral:7bwithqwen3:8bas the default Ollama model across config, tests, snapshots, and--initwizard"qwen3"/"qwen"asChatMLaliases inChatTemplate::parse_str— Qwen3 uses<|im_start|>/<|im_end|>tokens already supported by the existingChatMLvariantTest plan
cargo nextest run --workspace --lib --bins— 2830 tests passcargo clippy --workspace -- -D warnings— zero warningscargo +nightly fmt --check— cleanCloses #897