Skip to content
Find the best local LLM for your hardware, ranked by benchmarks
LLM Frameworks
Python
·
Latest v0.5.15 · 23d ago
Security brief →
Features
-
Auto-detects your GPU/CPU/RAM to rank compatible local LLMs
-
Provides evidence‑based ranking using live benchmark data
-
Simulates hardware before purchase (e.g., --gpu "RTX 4090")
-
Offers safe‑mode recommendations with VRAM headroom controls
No immediate action
v0.5.15
Bug fix
·
Flag validation
No immediate action
v0.5.14
New feature
·
VRAM estimates + Intel Arc detection
No immediate action
v0.5.13
Bug fix
·
Accurate search term matching
No immediate action
v0.5.12
New feature
·
Markdown output + speed filters
No immediate action
v0.5.11
New feature
·
Multi‑GPU support + T5 lineage
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
About
View on GitHub
Search tools, categories, lists, and users
Use ↑↓ to navigate, Enter to open, Esc to close
No results for ""
⌘K to open
↑↓ navigate
⏎ open