Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
Install
KitScout test notes
Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.
Similar tools
academy-guide193,970 ★ Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product
claude-api193,970 ★ Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, c
ccs-align116,728 ★ Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle ob
mode-creator116,728 ★ Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observa
html-ppt-hermes-cyber-terminal107,474 ★ OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Bui