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

v0.5.9 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

Updates Highlights, QA, and Local across a mixed release.

Type	Severity	Summary	CVE
Feature
Feature	Medium	GPU bandwidth detection now falls back to bundled TechPowerUp database for uncatalogued cards. GPU bandwidth detection now falls back to bundled TechPowerUp database for uncatalogued cards. Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Medium	Artificial Analysis Intelligence Index fetched live after App Router migration. Artificial Analysis Intelligence Index fetched live after App Router migration. Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Medium	Added MXFP4 and NVFP4 quantization support. Added MXFP4 and NVFP4 quantization support. Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Low	Added Apple M5-family simulation entries and Kepler-era Quadro catalog coverage. Added Apple M5-family simulation entries and Kepler-era Quadro catalog coverage. Source: llm_adapter@2026-06-10 Confidence: high	—
Feature	Low	Community GGUF repos without `base_model` metadata now match official benchmark scores by name. Community GGUF repos without `base_model` metadata now match official benchmark scores by name. Source: llm_adapter@2026-06-10 Confidence: high	—
Bugfix	Medium	Fixed AMD discrete GPU detection on Linux including RX 6750 XT. Fixed AMD discrete GPU detection on Linux including RX 6750 XT. Source: llm_adapter@2026-06-10 Confidence: high	—

Full changelog

GPU bandwidth detection now falls back to the bundled TechPowerUp database (2,824 GPUs) when a card is missing from the curated catalog. Uncatalogued cards no longer show BW: N/A with 0.0 tok/s estimates and oversized recommendations, and a laptop card can never inherit its desktop sibling's bandwidth. (#74, #98)
Fixed AMD discrete GPU detection on Linux, including RX 6750 XT and the compound lspci name path. (#61)
Artificial Analysis Intelligence Index is fetched live again after the site's App Router migration. Live scores overlay the curated snapshot, so coverage can only grow. (#87)
Added MXFP4 and NVFP4 quantization support. These repos were previously labeled FP16, overestimating VRAM by about 3.5x. (#27)
Added Apple M5-family simulation entries and Kepler-era Quadro catalog coverage.
Community GGUF repos without base_model metadata now match official benchmark scores by name.

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