About static quants of https://huggingface.co/apple/OpenELM 3B Instruct weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. Usage If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi part files. Provided Quants (sorted by size, not necessarily quality. IQ quants are often preferable over similar sized non IQ quants) Link Type Size/GB Notes : : : : GGUF Q2 K 1.3 GGUF IQ3 XS 1.4 GGUF IQ3 S 1.4 beats Q3 K GGUF Q3 K S 1.4 GGUF IQ3 M 1.5 GGUF Q3 K M 1.6 lower quality GGUF IQ4 XS 1.7 GGUF Q3 K L 1.8 GGUF Q4 K S 1.8 fast, recommended GGUF Q4 K M 2.0 fast, recommended GGUF Q5 K S 2.2 GGUF Q5 K M 2.3 GGUF Q6 K 2.6 very good quality GGUF Q8 0 3.3 fast, best quality GGUF f16 6.2 16 bpw, overkill Here is a handy graph by ikawrakow comparing some lower quality quant types (lower is better): And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 FAQ / Model Request See https://hugging…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy