hr98w/jev-visual

An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.

Open original source ↗

From the publisher

README & documentation

Source preview

Read the project’s overview, installation instructions and usage examples. The original README is the source of truth.

English · 简体中文 A small, runnable project for learning vision-language model inference on Apple Silicon. Use Qwen3.5-0.8B with MLX to answer multiple questions about one image: choose an option, judge yes/no, or score ordered levels. Includes a local browser UI, CLI and HTTP API. Breakout exposes the limits of Qwen3.5-0.8B-4bit in our non-thinking, direct-scoring setup. Asking it to follow the ball or choose Left/Right was unreliable: repeated choices could pin the paddle against an edge. The working approach simplifies the task: This reduces game control to visual classification, without a hidden ball tracker or solver. In a separate recorded test, 80 decisions produced 9 bricks cleared and 6 returns, with 2 lives remaining; the test stopped before completion. It is a simplified demo, not evidence of general game-playing ability. These trials do not isolate the effect of 4-bit quantization. Implementation and observations. Open /demo/ on the local server to try…

hr98w/jev-visual on GitHub A short preview, not the full document.

Read the full README ↗ · Preview checked 2026-09-22T12:35:18.540Z

Inside the original README — Document outline
  1. Jev Visual
  2. Visual game demos
  3. How Breakout is simplified
  4. Inference overview
  5. Run locally
  6. Learn the inference path
  7. Compare and verify
  8. Star History

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the README

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

What this repository does

An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.

Repository facts

Owner
hr98w
Primary language
Python
Stars
233
Forks
25
Open issues + pull requests
0
License
MIT
Archived
No
Default branch
main
Created
2026-09-17T17:45:56.000Z
Last push
2026-09-21T11:43:54.000Z

Topics and intended use

No topics were included in the latest source metadata.

Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.

Evaluate before installing

Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.

README and project files

Issues and maintenance discussion

Releases and changelog

Source and freshness

Source: GitHub. Metadata observed 2026-09-22T12:02:26.135Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related repositories

public-apis/public-apis

EbookFoundation/free-programming-books

donnemartin/system-design-primer

vinta/awesome-python

practical-tutorials/project-based-learning

NousResearch/hermes-agent