Kelheor
Kelheor
·
AI & ML interests
None yet
Recent Activity
new activity 5 days ago
Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF:Question about recent update new activity 6 days ago
unsloth/DeepSeek-V4-Flash-GGUF:Lower quants?Organizations
None yet
Question about recent update
#13 opened 5 days ago
by
Kelheor
Lower quants?
➕ 1
10
#2 opened 9 days ago
by
Kelheor
Excellent long-context capabilities, but issue with output repetition
6
#1 opened 14 days ago
by
Kelheor
ik_llama.cpp server crash
#7 opened 10 days ago
by
Kelheor
llama.cpp Eval bug: cache size limit reached, removing oldest entry
21
#11 opened 11 days ago
by
Kelheor
MTP draft model fails to load in llama.cpp — "invalid vector subscript" (gemma4-assistant arch)
4
#9 opened 26 days ago
by
Metod90
Uncensored: About Qwen3.6-35B-A3B-APEX-GGUF
❤️😎 1
2
#6 opened 3 months ago
by
CXK996
New uploads adds llama.cpp fixes
👍 6
16
#11 opened 3 months ago
by
danielhanchen
Commit description
👍 4
1
#10 opened 3 months ago
by
Kelheor
Please provide an uncensored version of Qwen 3.5 122B
❤️ 5
13
#2 opened 4 months ago
by
xldistance
Llama 3.1?
1
#2 opened almost 2 years ago
by
Kelheor
The V4 is here
👍 3
80
#11 opened about 3 years ago
by
TheYuriLover
Run the model with oobabooga/text-generation-webui - missing config.json, etc.
5
#6 opened over 3 years ago
by
mancub
USE 1.1 vicuna since it no longer has the issue of feedback / talkijng to its self?
2
#10 opened about 3 years ago
by
nucleardiffusion
Can't load the model
2
#5 opened over 3 years ago
by
Kelheor
Can't load the model
2
#5 opened over 3 years ago
by
Kelheor
Can't load the model
2
#5 opened over 3 years ago
by
Kelheor