Achhina's Digital Garden

Tag: llm

14 items with this tag.

  • Sep 09, 2026

    Local Open-Weight Model Shortlist 2026-09

    • llm
    • open-weights
    • local-inference
    • reference
  • Sep 09, 2026

    2026-09-02 Local Qwen3.5-4B Inference Baseline

    • journal
    • llm
    • docker
    • local-inference
    • claude-code
  • Sep 09, 2026

    2026-09-02 Open-Weight Model Shortlist for the M4 Max

    • journal
    • llm
    • open-weights
    • local-inference
    • research
  • Aug 08, 2026

    2026-08-09 OpenRouter Interceptor DeepSeek Flash Alias and a Stale Build

    • journal
    • llm
    • roleplay
  • Jul 07, 2026

    GLM 5.2 - Near-Frontier Open-Weight Coding Model

    • source
    • llm
    • open-weights
  • Jul 07, 2026

    Kimi K3 - Largest Open-Weight Model, Frontier-Trading Benchmarks

    • source
    • llm
    • open-weights
  • Jul 07, 2026

    2026-07-06 OpenRouter Interceptor Curated Model List

    • journal
    • llm
    • roleplay
  • Jul 07, 2026

    2026-07-17 GLM 5.2 Kimi K3 and Benchmark Note Refresh

    • journal
    • llm
    • benchmark
  • May 05, 2026

    Designing GenAI Evaluations - Process and Metrics

    • source
    • llm
    • evaluation
    • methodology
    • benchmark
    • metrics
  • May 05, 2026

    GEPA - Reflective Prompt Evolution Can Outperform Reinforcement Learning

    • source
    • llm
    • ai
    • evaluation
  • Apr 04, 2026

    LLM Benchmark Reference

    • llm
    • evaluation
    • ai
    • benchmark
    • 2-on-Arena
  • Apr 04, 2026

    LLM Comparison Sources

    • llm
    • leaderboards
    • evaluation
    • ai
  • Apr 04, 2026

    Autoresearch - Agent-Driven Autonomous ML Experimentation

    • ai-agents
    • llm
    • research-automation
    • karpathy
    • nanochat
  • Mar 05, 2026

    Small Local LLMs as Judges

    • research
    • llm
    • machine-learning
    • claude-code