Segmond Yunsai
segmond
AI & ML interests
None yet
Recent Activity
new activity about 2 months ago
ubergarm/DeepSeek-V3.2-Speciale-GGUF:Testing IQ5_K new activity about 2 months ago
unsloth/DeepSeek-V3.2-GGUF:Does this support DSA/lighting attention? new activity about 2 months ago
unsloth/Kimi-K2.5-GGUF:Q4_K_S versus Q3_K_XLOrganizations
Testing IQ5_K
🤗 1
4
#2 opened 3 months ago
by
shewin
Does this support DSA/lighting attention?
4
#1 opened about 2 months ago
by
segmond
Q4_K_S versus Q3_K_XL
2
#3 opened about 2 months ago
by
segmond
Jan 21: All GLM-4.7-Flash quants reuploaded - much better outputs!
🔥❤️ 7
29
#10 opened 2 months ago
by
danielhanchen
Thanks!
❤️ 2
5
#1 opened 7 months ago
by
segmond
Did you mistakenly delete UD-Q6_K_XL?
2
#4 opened 8 months ago
by
segmond
Good llama.cpp -ot offloading parameter for 24 GB / 32 GB cards?
1
#5 opened 9 months ago
by
qaraleza
Update the instructions on requirements
2
#10 opened 9 months ago
by
segmond
What sort of performance numbers are you seeing with llama.cpp and ik_llama?
6
#2 opened 9 months ago
by
segmond
gguf weights for llama.cpp?
👍🧠 24
1
#1 opened 10 months ago
by
segmond
gguf model?
👍 2
3
#1 opened 10 months ago
by
segmond
mmproj files missing?
1
#2 opened 10 months ago
by
segmond
New Q3_K_XL is excessively large, is this normal?
1
#15 opened 10 months ago
by
segmond
Please share feedback here!
34
#6 opened 10 months ago
by
shimmyshimmer
PR to llama.cpp?
1
#1 opened 11 months ago
by
segmond
How are these performing?
1
#1 opened 11 months ago
by
segmond
Lots of new UD quants
2
#1 opened 11 months ago
by
segmond
Can you make Q8?
👍 1
1
#2 opened 11 months ago
by
segmond
LMS Q4KM only 16k Context
5
#1 opened about 1 year ago
by
JJ404GO
Getting error with Q3-K-M
7
#2 opened about 1 year ago
by
alain401