Skip to content

## 🧪 FastFlowLM v0.9.1 — Quantization Upgrade & Log Improvements

Choose a tag to compare

View all tags
@FastFlowLM FastFlowLM released this 30 Jul 17:59
· 1344 commits to main since this release
v0.9.1
bec7aa6
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

FastFlowLM v0.9.1 introduces improved quantization for smaller Qwen3 models and cleaner logging in server mode.

✨ What's New

🧠 1. Improved Quantization for Qwen3 Small Models

  • Switched Qwen3:0.6b and Qwen3:1.7b from manual AWQ quantization to Unsloth Q4_1.
  • This improves model compatibility and performance on constrained environments.

📉 2. Optimized Server Logs

  • Cleaner and more informative terminal logs in serve mode.
  • Makes it easier to monitor requests, model reloads, and runtime behavior.

✅ Usage Recap

Interactive CLI:

flm run qwen3:0.6b
flm run qwen3:1.7b prompt.txt

Server Mode:

flm serve

Model Management:

flm list
flm remove qwen3:0.6b

This release continues to streamline FastFlowLM’s performance and developer experience, especially for lightweight deployment targets.

Assets 3
Loading