sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-01 14:44:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

download : prefer q8_0 when q4_k not available

Browse Source
This commit is contained in:
Georgi Gerganov
2026-04-27 12:08:25 +03:00
parent 0f1bb602dd
commit fd6f79c7a4
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/download.cpp
View File

@@ -627,7 +627,7 @@ static hf_cache::hf_file find_best_model(const hf_cache::hf_files & files,
if (!tag.empty()) {
tags.push_back(tag);
} else {
tags = {"Q4_K_M", "Q4_0"};
tags = {"Q4_K_M", "Q8_0"};
}
for (const auto & t : tags) {