Find the best local LLM for your hardware, ranked by benchmarks

v0.5.8 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo LLM Frameworks

✓ No known CVEs patched

✓ No known CVEs patched in this version

Topics

ai apple-silicon benchmarks cli gguf gpu

+7 more

huggingface inference llm local-llm ollama python vram

Summary

AI summary

Fixed ranking regression for A3000 Laptop 6GB.

Type	Severity	Summary	CVE
Feature
Feature	Low	Adds retry/backoff for transient Hugging Face and benchmark fetch failures. Adds retry/backoff for transient Hugging Face and benchmark fetch failures. Source: llm_adapter@2026-06-05 Confidence: high	—
Feature	Low	Adds GPU catalog coverage for A3000 Laptop, RTX 3050, RTX 5060, RTX 5070 Ti, RX 9070, and RX 9070 XT. Adds GPU catalog coverage for A3000 Laptop, RTX 3050, RTX 5060, RTX 5070 Ti, RX 9070, and RX 9070 XT. Source: llm_adapter@2026-06-05 Confidence: high	—
Feature	Low	Adds context-length shorthand and benchmark source/confidence metadata in JSON output. Adds context-length shorthand and benchmark source/confidence metadata in JSON output. Source: llm_adapter@2026-06-05 Confidence: high	—
Bugfix	Medium	Fixes A3000 Laptop 6GB ranking regression. Fixes A3000 Laptop 6GB ranking regression. Source: llm_adapter@2026-06-05 Confidence: high	—
Bugfix	Medium	Improves error message when fetching models with network exceptions lacking a message. Improves error message when fetching models with network exceptions lacking a message. Source: llm_adapter@2026-06-05 Confidence: high	—

Full changelog

Fixed the A3000 Laptop 6GB ranking regression.
Added retry/backoff for transient Hugging Face and benchmark fetch failures.
Improved Error fetching models output when network exceptions have no message.
Added GPU catalog coverage for A3000 Laptop, RTX 3050, RTX 5060, RTX 5070 Ti, RX 9070, and RX 9070 XT.
Added context-length shorthand and benchmark source/confidence metadata in JSON output.

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.

Share this release

Track Find the best local LLM for your hardware, ranked by benchmarks

Get notified when new releases ship.

About Find the best local LLM for your hardware, ranked by benchmarks