Quantizing Models Bitsandbytes
Skill Verified ActiveQuantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
Quantize LLMs to reduce memory usage by 50-75% with minimal accuracy loss, enabling larger models on limited hardware and faster inference.
Features
- Quantizes LLMs to 8-bit or 4-bit
- Supports INT8, NF4, FP4 formats
- Enables QLoRA training
- Integrates with HuggingFace Transformers
- Reduces memory by 50-75%
Use Cases
- Fitting larger models into limited GPU memory
- Achieving faster LLM inference speeds
- Fine-tuning large models on consumer GPUs with QLoRA
- Reducing optimizer memory during training with 8-bit optimizers
Non-Goals
- Replacing advanced inference optimization frameworks like GPTQ or AWQ
- Providing CPU-only inference solutions like GGUF
- Supporting hardware without tensor core acceleration
Trust
- info:Issues Attention17 issues opened and 4 closed in the last 90 days indicates a closure rate below 50% with a moderate number of open issues.
Installation
npx skills add davila7/claude-code-templatesRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
VerifiedTrust Signals
Similar Extensions
Quantizing Models Bitsandbytes
97Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
Arize Prompt Optimization
100Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.
Unsloth
100Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Prompt Optimization
100Applies prompt repetition to improve accuracy for non-reasoning LLMs
Vector Index Tuning
99Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
Transformers
98This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.