repoGitHubTrust 82 · PrimaryPublished 2h agoLive · 2h ago
drumih/turbo-fieldfare
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%SOTA Apple Silicon Inference (August 15, 2026) →
- PossiblePossibly related (embedding) · 54%Apple M7 Ultra Chip Planned With Up to 1.5 TB of Unified Memory →
- PossiblePossibly related (embedding) · 53%Gemma 4 12B - MLX Kernel →
- PossiblePossibly related (embedding) · 51%I mapped which local LLMs actually fit each RAM tier, 8 to 128GB (open dataset) →
- PossiblePossibly related (embedding) · 50%Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong →
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “Tongyi-MAI/Z-Image-Turbo” ≈ “drumih/turbo-fieldfare””
- FuzzySimilar title/name (fuzzy) · 59%openai/whisper-large-v3-turbo →
“Fuzzy title match (0.73): “openai/whisper-large-v3-turbo” ≈ “drumih/turbo-fieldfare””
Covers
Related to (incoming)
Related across the graph
newsApple M7 Ultra Chip Planned With Up to 1.5 TB of Unified MemorynewsI mapped which local LLMs actually fit each RAM tier, 8 to 128GB (open dataset)modelopenai/whisper-large-v3-turbonewsSOTA Apple Silicon Inference (August 15, 2026)newsShow HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrongmodelTongyi-MAI/Z-Image-TurbonewsGemma 4 12B - MLX Kernel