repoGitHubTrust 82 · PrimaryPublished 4d agoLive · 4d ago
TristanBilot/mlx-benchmark
Benchmark of Apple MLX operations on all Apple Silicon chips (GPU, CPU) + MPS and CUDA.
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) · 61%Liquid AI Open-Sources Pipette: A Reproducible Benchmarking Suite That Measures On-Device Models, Quantization, Runtime and Hardware Together - MarkTechPost →
- PossiblePossibly related (embedding) · 58%Gemma 4 12B - MLX Kernel →
- PossiblePossibly related (embedding) · 57%SOTA Apple Silicon Inference (August 15, 2026) →
- PossiblePossibly related (embedding) · 55%We'll benchmark an Open weights LLM on any GPU you choose — drop your model + hardware and we'll run it. [D] →
- PossiblePossibly related (embedding) · 52%What Nvidia's first Groq 3 LPU benchmarks tell us about its $20B gamble →
- PossiblePossibly related (embedding) · 47%ExLlamaV3 is underrated →
Covers
newsLiquid AI Open-Sources Pipette: A Reproducible Benchmarking Suite That Measures On-Device Models, Quantization, Runtime and Hardware Together - MarkTechPostnewsGemma 4 12B - MLX KernelnewsSOTA Apple Silicon Inference (August 15, 2026)newsWe'll benchmark an Open weights LLM on any GPU you choose — drop your model + hardware and we'll run it. [D]newsWhat Nvidia's first Groq 3 LPU benchmarks tell us about its $20B gamble
Covers (incoming)
Related across the graph
newsLiquid AI Open-Sources Pipette: A Reproducible Benchmarking Suite That Measures On-Device Models, Quantization, Runtime and Hardware Together - MarkTechPostnewsSOTA Apple Silicon Inference (August 15, 2026)newsWe'll benchmark an Open weights LLM on any GPU you choose — drop your model + hardware and we'll run it. [D]newsWhat Nvidia's first Groq 3 LPU benchmarks tell us about its $20B gamblenewsExLlamaV3 is underratednewsGemma 4 12B - MLX Kernel