toolAngestromTrust 64Published 3mo agoLive · 2mo ago
QuantBench
A one-click quantization and benchmarking tool.
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownQuantization at 1.58 bits →
- LinkedLinked via unknownquant-kit →
- LinkedLinked via unknownQuantization →
- LinkedLinked via unknownQwen 3.6 27B Speculative Decoding Bench: Pushing ~100 TPS on a single RTX 3090 →
- LinkedLinked via unknownGSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache →
- LinkedLinked via unknown$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Space →
- PossiblePossibly related (embedding) · 45%Sagargupta16/claude-cost-optimizer →
- PossiblePossibly related (embedding) · 52%qualcomm/aimet →
Related to
Covers (incoming)
Related to (incoming)
paperGSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cachepaper$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic SpacerepoSagargupta16/claude-cost-optimizerrepoqualcomm/aimetrepoquantbelt/jupyter-quantrepolucidrains/vector-quantize-pytorchrepobitsandbytes-foundation/bitsandbytesrepoHIPS/autogradrepoLLMQuant/quant-mindrepodavisking/dlibrepopubmethod/quantizationpaperKroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers
Related across the graph
repoquantbelt/jupyter-quantrepobitsandbytes-foundation/bitsandbytesrepoHIPS/autogradrepolucidrains/vector-quantize-pytorchpaperKroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion TransformersnewsQwen 3.6 27B Speculative Decoding Bench: Pushing ~100 TPS on a single RTX 3090news[R] Statistically-Lossless Quantization of Large Language ModelspaperQuantization at 1.58 bitsglossary_termQuantizationrepoquant-kitnewsPrism-ML's Bonsai-27B BenchmarksrepoSagargupta16/claude-cost-optimizernews[Paper] Statistically-Lossless Quantization of Large Language ModelspaperGSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cacherepoqualcomm/aimetrepodavisking/dlibrepoLLMQuant/quant-mindrepopubmethod/quantizationpaper$\text{Log}_\text{b}$Quant: Quantizing Language Models in Logarithmic Space