repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago
ohdearquant/lattice
Run, quantize, and fine-tune LLMs on Apple Silicon. Pure Rust, no Python, no CUDA, no ONNX
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) · 52%OpenAI and Broadcom announce chip designed for LLM inference at scale →
- PossiblePossibly related (embedding) · 46%How're you deploying LLMs in production now-a-days? What's the best and most affordable way? [D] →
- PossiblePossibly related (embedding) · 46%I mapped which local LLMs actually fit each RAM tier, 8 to 128GB (open dataset) →
- PossiblePossibly related (embedding) · 46%IBM’s new Granite 4.2 models ride the wave of interest in local LLMs - Ars Technica →
- PossiblePossibly related (embedding) · 46%IBM's new Granite 4.2 models ride the wave of interest in local LLMs - Ars Technica →
- PossiblePossibly related (embedding) · 51%LLM-based platform for generating new materials synthesis recipes dramatically cuts trial and error - Phys.org →
- PossiblePossibly related (embedding) · 51%DynaMiCS: Fine-Tuning LLMs with Performance Constraints Using Dynamic Mixtures - Apple Machine Learning Research →
Covers
Covers (incoming)
newsIBM’s new Granite 4.2 models ride the wave of interest in local LLMs - Ars TechnicanewsIBM's new Granite 4.2 models ride the wave of interest in local LLMs - Ars TechnicanewsLLM-based platform for generating new materials synthesis recipes dramatically cuts trial and error - Phys.orgnewsDynaMiCS: Fine-Tuning LLMs with Performance Constraints Using Dynamic Mixtures - Apple Machine Learning Research
Related across the graph
newsOpenAI and Broadcom announce chip designed for LLM inference at scalenewsDynaMiCS: Fine-Tuning LLMs with Performance Constraints Using Dynamic Mixtures - Apple Machine Learning ResearchnewsIBM’s new Granite 4.2 models ride the wave of interest in local LLMs - Ars TechnicanewsLLM-based platform for generating new materials synthesis recipes dramatically cuts trial and error - Phys.orgnewsI mapped which local LLMs actually fit each RAM tier, 8 to 128GB (open dataset)newsIBM's new Granite 4.2 models ride the wave of interest in local LLMs - Ars TechnicanewsHow're you deploying LLMs in production now-a-days? What's the best and most affordable way? [D]