skill
quantizing-models-bitsandbytes Review findings
orchestra-researchorchestra-research/ai-research-skillsupdated
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 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
- Stars
- 14,234
- Version
- v1
- Copies
- 0
Overview
Waxell's checks found 3 findings to review, highest severity high.
- Highest severity
- high
- Findings
- 3
- What ran
- Static analysis
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked 2 days ago
Result
Review findings Waxell's checks found 3 findings to review, highest severity high.
Checked with static analysis: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. Nothing was run. How the checks work
Findings (3)
high · 3
- high
Tells Claude to install unpinned packages (bitsandbytes, transformers, accelerate)
SKILL.md:19 · skill_risk:S2
- high
Tells Claude to install unpinned packages (bitsandbytes, transformers, peft, accelerate, datasets)
SKILL.md:154 · skill_risk:S2
- high
Tells Claude to install unpinned packages (bitsandbytes)
SKILL.md:338 · skill_risk:S2
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
One version so far: v1 (1.0.0), seen 2026-11-03.
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More research skills and plugins
- optimizing-attention-flashorchestra-researchOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers… Review findingsResearchDocuments14k
- gguf-quantizationorchestra-researchGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or… Review findingsResearchEngineering14k
- gptqorchestra-researchPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when… Review findingsResearchDocuments14k
- evaluating-llms-harnessorchestra-researchEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality,… Review findingsResearchDocuments14k