~ / leaderboard / skill / quantizing-models-bitsandbytes
Skill · #3692
quantizing-models-bitsandbytes
Quantizes 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 fo
5rigs use it
0%of all rigs
7.4kavg rig context tax
Get it
$ npx degit Yichen-ZJU/lemvo/claude/skills/bitsandbytes .claude/skills/quantizing-models-bitsandbytes From the most-starred rig that ships it: Yichen-ZJU/lemvo. Same-named skills in different rigs may differ — review before use.
Often used together with
clip · 5awq-quantization · 5deepspeed · 5evaluating-llms-harness · 5gguf-quantization · 5gptq · 5grpo-rl-training · 5huggingface-accelerate · 5knowledge-distillation · 5long-context · 5
Rigs using quantizing-models-bitsandbytes (5)
Yichen-ZJU/lemvo
Lemvo — a research agent that thinks and acts. One research system, two CLI engines: Claude Code and Codex CLI.
Skill Collector 6.8k tok · · Q0
Yichen-ZJU/lemvo-for-claude
Lemvo for Claude Code — choose routes, build methods, learn from experiments, and write discoveries. 115 skills, two research loops, shared project memory.
Skill Collector 7.1k tok · · Q0
Yichen-ZJU/claude-for-research
Autonomous research for Claude Code: literature, ideas, unattended experiments, writing and review. 115 skills, two loops.
Skill Collector 7.0k tok · · Q0
TrainToGPB/agentic-coding-setup
Personal Claude Code setup for LLM engineering — custom agents, skills, and a library organized by context
Skill Collector 6.6k tok · · Q0
KiaroSama/Numera-Skill-Forge
Turn standalone AI skills into installable plugins for Claude, Codex, and other agents, with a launcher that keeps them synced with their upstream repositories.
Skill Collector 9.4k tok · · Q15