Add Quickstart section to README#438
Open
sethconvex wants to merge 1 commit into
Open
Conversation
Consolidate build, model download, and run steps (CLI, interactive, and server) into a single actionable Quickstart near the top, with cross-links to Model Weights and SSD streaming and the macOS CPU-build warning. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds a
## Quickstartsection near the top of the README, right after the intro/backends list and before "Motivations".Why
The build, model-download, and run steps were scattered across the README (Model Weights, the "Then build" snippet, the CLI section, the Server section), with no single actionable "how do I start" path for a new reader. This consolidates them into one place.
What it covers
make/make cuda-spark/make cuda-generic/make cpu)./download_model.sh q2-imatrix) with a note that it's resumable and pulls tens of GB into./gguf/Every command in the section was verified end to end on an M5 Max / 128 GB: built with
make, downloaded the 86.7 GBq2-imatrixFlash GGUF, and ran a one-shot prompt (~24 t/s generation).🤖 Generated with Claude Code