image 7 palette 6 compression 5 llm 4 trade 4 share 4 quotation 4 color 4 stock 4 typescript 3 wasm 3 gif 3 machine-learning 3 jupyter 3 jupyterlab 3 jupyterlab-extension 3 auto-tuning 3 knowledge-distillation 3 large-language-models 3 low-precision 3 post-training-quantization 3 pruning 3 quantization-aware-training 3 smoothquant 3 sparsity 3 node 3 ai 3 sparsegpt 2 self-hosted 2 natural-language-processing 2 model-compression 2 mixtral 2 mistral 2 llms 2 llm-inference 2 gptq 2 fp4 2 kmeans 2 awq 2 large-language-model 2 nodejs 2 quantize 2 llama 2 llama3 2 llama2 2 offline 2 javascript 2 color-reduction 2 optimization 2 efficient-inference 2 png 2 webassembly 2 gemma 2 memory-optimization 2 mxformat 2 generative-ai 2 language-model 2 language-models 2 int8 2 int4 2 stats 1 multi-provider 1 inference 1 gpu 1 vram 1 performance 1 benchmark 1 local-ai 1 sllm 1 apple-silicon 1 stdlib 1 small-language-models 1 stdmath 1 ollama 1 stdml 1 ml 1 machine 1 learning 1 mathematics 1 math 1 statistics 1 ai-agents 1 huggingface 1 gemini 1 rust 1 deep-learning 1 server 1 browser 1 web-worker 1 TA-Lib 1 talib 1 tdx 1 node-js 1 lloyds-algorithm 1 data-mining 1 accumulator 1 incremental 1 partition 1 cluster 1 clusters 1