Q Change
qikchen
·
AI & ML interests
None yet
Organizations
None yet
Are the F16 weights upcasted MXFP4? -- Why no `gpt-oss-20b-MXFP4.gguf`?
3
#34 opened 3 months ago
by
rtzurtz
Chat template + tool calling fixes
❤️
🔥
3
21
#3 opened 7 months ago
by
shimmyshimmer
Optimal Quants from a performance perspective on Apple Sillicon
2
#5 opened 7 months ago
by
qikchen
Optimal Quants from a performance perspective on Apple Sillicon
2
#5 opened 7 months ago
by
qikchen
Chat template + tool calling fixes
❤️
🔥
3
21
#3 opened 7 months ago
by
shimmyshimmer
Chat template + tool calling fixes
❤️
🔥
3
21
#3 opened 7 months ago
by
shimmyshimmer