Myron Jones PRO
kingjones777
AI & ML interests
None yet
Recent Activity
new activity 10 days ago
kingjones777/Qwen3.8-Flash-Next-Uncensored-ROCmFP4-STRIX_LEAN-GGUF:How do I use the MTP? new activity 10 days ago
kingjones777/Qwen3.8-Flash-Next-MTP-Heads-GGUF:Crashes when analyzing imagesOrganizations
None yet
Does this means it's not recommended to use for now untill TheROCK fixes it?
1
#1 opened 12 days ago
by
sn3d9
How do I use the MTP?
3
#1 opened 11 days ago
by
sn3d9
Crashes when analyzing images
1
#1 opened 11 days ago
by
sn3d9
Question on the AMD/ROCm path for Xing4.0
1
#1 opened 15 days ago
by
Prophet000
Thank you for bringing Apodex-1.1-mini to the GGUF community!
🔥 1
1
#1 opened about 1 month ago
by
Selene999
STRIX_LEAN long-context numbers from my GTR9 Pro — plus two small questions when you have a moment
11
#6 opened about 1 month ago
by
liusecret
Question about performance overall
1
#3 opened about 1 month ago
by
sn3d9
Field report: MTP draft works great on Windows/gfx1151, but you need a new repo installaltion
2
#1 opened about 1 month ago
by
beeugene
Q6 AGENT (ftype 114) on ROCm — MTP gives ~0 gain on gfx1151; prefill/bandwidth data inside
2
#1 opened about 1 month ago
by
liusecret
Feature request: Uncensored Ornith-1.5-35B-A3B in ROCmFP4
4
#2 opened about 1 month ago
by
liusecret
Thanks & MTP Query
🔥👍 2
4
#5 opened about 1 month ago
by
jesseb4me
Compatible llama.cpp
4
#4 opened about 1 month ago
by
FormatC
which llama.cpp fork needs to be used?
2
#1 opened about 1 month ago
by
cygnal
pp, is this a typo?
👍 1
2
#2 opened about 1 month ago
by
auf1r2
Hello! Did you try bigger size with mmap?
7
#2 opened about 1 month ago
by
auf1r2
Awesome!
1
#1 opened about 1 month ago
by
cafonez
Why is not 256k at full context?
1
#3 opened about 1 month ago
by
qZitronen
ctx-size 2048.. Really?
1
#1 opened about 1 month ago
by
dany404
How about rocmfp8?
4
#1 opened about 2 months ago
by
joelw7