Search: Quantization
18 result(s) on page 1
Local_Model_Quantization_Router
Recommend local LLM model routes and quantization levels using hardware, privacy, task complexity, context size, and budget constraints. Use for Qwen/Ollama/...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Local_Model_Quantization_RouterRDK_X5_Toolchain_Quantization
Toolchain-level skill for D-Robotics / Horizon Robotics RDK X5 OpenExplorer v1.2.8 post-training quantization (PTQ). Use when converting arbitrary ONNX model...
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__RDK_X5_Toolchain_Quantizationawq-quantization
Indexed by skills.sh from davila7/claude-code-templates
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.5
- Author
- davila7
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__awq-quantizationgguf-quantization
Indexed by skills.sh from davila7/claude-code-templates
quarantinedskills.sh- Registry
- skills.sh
- Category
- Mlops· inferred
- Version
- 1.0.5
- Author
- davila7
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__gguf-quantizationhqq-quantization
Indexed by skills.sh from davila7/claude-code-templates
quarantinedskills.sh- Registry
- skills.sh
- Version
- 1.0.5
- Author
- davila7
curl -s /v1/skills/community__axehub:skills.sh__skills.sh__hqq-quantizationserving-llms-vllm
vLLM: high-throughput LLM serving, OpenAI API, quantization.
quarantinedlinuxmacosvLLMoptional- Registry
- optional
- Category
- MLOps
- Version
- 1.0.0
- Author
- Orchestra Research
- License
- MIT
curl -s /v1/skills/community__axehub:optional__optional__serving-llms-vllmEcoCompute_—_LLM_Energy_Efficiency_Advisor
Evidence-first, stateless consulting skill for LLM inference energy optimization using measured benchmark priors and anti-pattern detection.
quarantinedai-mlcarbon-footprintenergy-efficiencyClawHub- Registry
- ClawHub
- Category
- AI Agents
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__EcoCompute_—_LLM_Energy_Efficiency_AdvisorTurboQuant+_KV_Cache_Compression
TurboQuant+ compresses llama.cpp KV caches on Apple Silicon up to 6.4x with minimal quality loss, enabling larger models and longer contexts efficiently.
quarantinedllmquantizationClawHub- Registry
- ClawHub
- Category
- AI Agents
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__TurboQuant+_KV_Cache_Compressionllama-cpp
llama.cpp local GGUF inference + HF Hub model discovery.
quarantinedlinuxmacoswindowsoptional- Registry
- optional
- Category
- MLOps
- Version
- 1.0.0
- Author
- Orchestra Research
- License
- MIT
curl -s /v1/skills/community__axehub:optional__optional__llama-cppollama-model-management
verifiedFirst-party- Registry
- First-party
- Category
- General
- Version
- 1.0.0
- Author
- AXE
- License
- MIT
curl -s /v1/skills/ollama-model-managementBox-KVCache
Local KV Cache compression for LLMs using low-rank decomposition and INT8 quantization to reduce GPU memory by 2-4x during inference.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Box-KVCacheHardware_Llm_Optimizer
Auto-detect PC hardware (CPU/GPU/RAM/VRAM) -> Determine max LLM parameters -> Recommend models (3B/7B/8B/13B/34B/70B) + quantization + deployment tools + bot...
quarantinedaichinesehardwareClawHub- Registry
- ClawHub
- Category
- AI Agents
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Hardware_Llm_OptimizerLLM_Inference_Performance_Estimator
Estimate LLM inference performance metrics including TTFT, decode speed, and VRAM requirements based on model architecture, GPU specs, and quantization format.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__LLM_Inference_Performance_EstimatorOpensearch_Vector_Search
Amazon OpenSearch vector search expert knowledge base. Comprehensive guidance on vector search configuration, cluster tuning, quantization, cost optimization...
quarantinedawsknnopensearchClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__Opensearch_Vector_SearchTurboQuant_Memory
Compress and accelerate vector search in memory/RAG systems using TurboQuant (ICLR 2026) — near-optimal vector quantization with 5-8x compression and 98%+ se...
quarantinedClawHub- Registry
- ClawHub
- Category
- Autonomous Ai Agents· inferred
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__TurboQuant_Memoryllmfit
Detect local hardware (RAM, CPU, GPU/VRAM) and recommend the best-fit local LLM models with optimal quantization, speed estimates, and fit scoring.
quarantinedClawHub- Registry
- ClawHub
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:ClawHub__ClawHub__llmfittao-train-image-classification
PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO image-classification…
quarantinedimageclassificationNVIDIA- Registry
- NVIDIA
- Category
- Vision AI
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__tao-train-image-classificationtao-train-rtdetr
RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and quantization for deployment optimization. Use when training, evaluating, distilling, quantizing, exporting, or running in…
quarantinedobjectdetectionNVIDIA- Registry
- NVIDIA
- Category
- Vision AI
- Version
- 1.0.0
curl -s /v1/skills/community__axehub:NVIDIA__NVIDIA__tao-train-rtdetr