quant-formats
quant-formats is a Local & open models skill for AI agents, published by kekzl in the imp repository on GitHub. Skillspace rates quant-formats D (64/100) and it passed the safety scan; the rating is based on static analysis only.
Use when working on imp's quantization formats, loaders, or dequant paths — GGUF Q4_0…Q8_0/Q*_K/IQ4/MXFP4, NVFP4 two-level scaling, FP8 E4M3, StorageTier, decode cache, KV-cache dtypes, "which quant should I use", scale-factor layout, dequant kernel wiring. Do NOT use for writing/optimizing GEMM/GEMV kernels (sm120-cuda-expert) or measuring quant perf (benchmark-cuda).
- Grade
- D
- Quality
- 64 / 100
- Safety
- Passed
- GitHub stars
- 30
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Repo-internal: written for the repository it lives in. Covers imp's own quant pipeline, docs and dequant wiring
What the scanner flagged
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.