Quantizing Models Bitsandbytes
This handles the setup for quantizing large language models using the bitsandbytes library, which is exactly what you need when a model won't fit in your GPU memory. The skill gives you ready-to-use code for both 8-bit quantization (cuts memory in half) and 4-bit quantization (75% reduction), with minimal accuracy loss according to the docs. It's a straightforward implementation helper rather than anything fancy. If you're running local LLMs and hitting OOM errors, this gets you the boilerplate to compress models down to size. The skill has passed most security audits and has decent traction with 342 installs.
- skills.sh installs
- 337
- GitHub stars
- 33.2K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add davila7/claude-code-templates --skill quantizing-models-bitsandbytes --agent claude-codeInstalls into .claude/skills of the current project.
Files
This handles the setup for quantizing large language models using the bitsandbytes library, which is exactly what you need when a model won't fit in your GPU memory. The skill gives you ready-to-use code for both 8-bit quantization (cuts memory in half) and 4-bit quantization (75% reduction), with minimal accuracy loss according to the docs. It's a straightforward implementation helper rather than anything fancy. If you're running local LLMs and hitting OOM errors, this gets you the boilerplate to compress models down to size. The skill has passed most security audits and has decent traction with 342 installs.
Browse the repository on GitHubSponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/davila7/claude-code-templates
- Category
- Data Science & ML
- First seen
- Jun 3, 2026
More from davila7/claude-code-templates
All 618- Nemo Curator336
- Discord Bot Architect335
- Railway Deploy335
- Aws Serverless334
- Clip334
- Datadog Cli334
- Lint And Validate334
- Notion Meeting Intelligence334
- Speculative Decoding334
- Web Artifacts Builder334
- Move Code Quality333
- Email Sequence332
- Nemo Guardrails332
- Optimizing Attention Flash332
- Figma331
- Zapier Workflows330
- Scikit Survival329
- Axolotl328
- Developer Growth Analysis328
- Alphafold Database326
- Llm App Patterns326
- Gh Fix Ci325
- Pyhealth325
- Scanpy325
Recommended
More Data Science & ML
lead-generation-and-demandmanojbajaj95/claude-gtm-pluginComprehensive B2B demand generation and lead acquisition skill. Use when building lead generation systems, creating demand acquisition campaigns, optimizing CAC336skills.sh installs
raise-negotiation-preponewave-ai/claude-skillsMarket salary research, accomplishment quantification, negotiation scripts, total compensation analysis, timing strategy.336skills.sh installs
notion-meeting-intelligencedavila7/claude-code-templatesPrepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.334skills.sh installs
paper-polisheyh0602/skillshubThis skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, LaTeX best practices, and document structu334skills.sh installs
consulting-frameworksaznatkoiny/zai-skillsCore consulting thinking frameworks and methodologies for structuring business problems, communicating findings, analyzing strategy, building financial models, 333skills.sh installsoptimizing-attention-flashdavila7/claude-code-templatesOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>332skills.sh installs