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
reverse-engineer-anything456,653 ★ Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and b
scaffold-exercises323,485 ★ Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use
wait-what323,485 ★ Stop. That last message did not land: re-pitch it.
template-skill193,970 ★ Replace with description of the skill and when Claude should use it.
ponytail-debt190,107 ★ List every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing