Georgy Gufiyzev
GeorgyGUF
AI & ML interests
I make VLMs, LLMs and image models low ranked adapters more accessible.
Organizations
None yet
Request for BF16 GGUF
👍
1
1
#1 opened 3 months ago
by
GeorgyGUF
cosmos-predict2-2b-t2i-ex-q2_k.gguf
20
#3 opened 6 months ago
by
GeorgyGUF
Broken with latest llama.cpp
2
#1 opened 6 months ago
by
GeorgyGUF
bf16 is now broken. Latest llama.cpp
2
#6 opened 6 months ago
by
GeorgyGUF
wan2.1-i2v-480p-14b-f32 fix try (looks like bad try, but still better then current)
#19 opened 7 months ago
by
GeorgyGUF
Wan2.1 14B T2V fp32 fix try (works, but really properly?)
#18 opened 7 months ago
by
GeorgyGUF
Wan2.1 14B T2V fp32 fix try (works, but really properly?)
#18 opened 7 months ago
by
GeorgyGUF
Wan2.1 14B fp32 ggufs are corrupt? Request for bf16 / f16 / special quantizations, fun model and proper text_encoder&VAE&workflows.
43
#16 opened 7 months ago
by
GeorgyGUF
wan2.1-i2v-480p-14b-f32 fix try (looks like bad try, but still better then current)
#19 opened 7 months ago
by
GeorgyGUF
wan2.1-i2v-480p-14b-f32 fix try (looks like bad try, but still better then current)
#19 opened 7 months ago
by
GeorgyGUF
Wan2.1 14B fp32 ggufs are corrupt? Request for bf16 / f16 / special quantizations, fun model and proper text_encoder&VAE&workflows.
43
#16 opened 7 months ago
by
GeorgyGUF
Wan2.1 14B T2V fp32 fix try (works, but really properly?)
#18 opened 7 months ago
by
GeorgyGUF