We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Update llama.cpp量化部署.md
update plus-33b stats
prepare for plus-33b stats
cleaning
update steps for k-quants series
update 33b speed
update speed
update new quant
update q2_k and q6_k speed
update speed test
update wiki to v4.0
update new quant methods performance
Update llama.cpp量化部署.md finish testing 33B speed
update notice on pull the latest code
Update llama.cpp量化部署.md - 33b alpha test results (subject to changes)
update llama.cpp usage
Updated llama.cpp量化部署 (markdown)
update speed perf. for the latest llama.cpp
update 13b stats
update quantization perf. comparison
remove q4_3 which is not competitive than others
remove 'experimental' note on Q5/Q8. they are officially supported now.
add q5 and q8 quant.
fix broken links