Back to browse
An opinionated ranking of 21 open-weight LLMs, filterable by your GPU

An opinionated ranking of 21 open-weight LLMs, filterable by your GPU

by AndrewLiu96·Jun 24, 2026·2 points·1 comment

AI Analysis

●●SolidNiche GemBig Brain

Opinionated LLM rankings with actual GPU memory math, not just benchmark scores.

Strengths
  • Hardware-focused filtering with practical VRAM calculations per model.
  • Six capability grades beyond raw benchmarks with clear methodology.
  • Monthly updates with freshness stamps and sourced benchmark data.
Weaknesses
  • Only 21 models limits coverage compared to Hugging Face Open LLM Leaderboard.
  • Opinionated ranking may not match specific use case requirements.
Category
Target Audience

Developers self-hosting or deploying open-weight models

Similar To

LMArena · Artificial Analysis Intelligence Index · Hugging Face Open LLM Leaderboard

Similar Projects

AI/ML●●●Banger

Sleeping LLM – A language model that remembers by sleeping

Direct weight editing for persistent memory—MEMIT meets LoRA consolidation with null-space math.

WizardryBig BrainZero to One
vbaranov87
203mo ago