Skip to content
Open-Source Registry

cargo / rlx-gguf-convert

rlx-gguf-convert

bitbison: no public build no release has built yet

Convert safetensors / ONNX initializer tensors into GGUF with per-tensor quantization. Useful for shrinking a model's on-disk + in-memory footprint at first load and reusing the GGUF dump on subsequent runs.

282 downloads · source · home page autodiffcompilermlneural-networktensor View on crates.io

0.2.18 did not build; the badge stands for .

Versions13RiskVulnsPublished
0.2.18did not build1d ago
0.2.17not analyzed2026-10-04
0.2.16not analyzed2026-09-16
0.2.14not analyzed2026-08-12
0.2.13not analyzed2026-07-19
0.2.12not analyzed2026-07-07
0.2.11not analyzed2026-07-06
0.2.10not analyzed2026-06-29
0.2.9not analyzed2026-06-22
0.2.8not analyzed2026-06-21
0.2.6not analyzed2026-06-11
0.2.5not analyzed2026-06-10
0.2.4not analyzed2026-06-09