noctrex
noctrex
AI & ML interests
None yet
Recent Activity
new activity
about 1 hour ago
noctrex/Ring-mini-sparse-2.0-exp-MXFP4_MOE-GGUF:Can this model handle 128K context?
updated
a model
1 day ago
noctrex/Ring-mini-sparse-2.0-exp-MXFP4_MOE-GGUF
updated
a model
2 days ago
noctrex/Qwen3-Coder-Next-MXFP4_MOE-GGUF
Organizations
None yet
Can this model handle 128K context?
6
#1 opened 1 day ago
by
TomLucidor
Feb 4: Qwen3-Coder-Next GGUFs reuploaded - much better outputs!
🤗
👍
13
19
#5 opened 3 days ago
by
danielhanchen
Is this static quantization without using imatrix?
4
#3 opened 3 days ago
by
MrPippin
Phenomenal model
2
#1 opened 14 days ago
by
spanspek
Interesting Output
1
#1 opened 4 days ago
by
wonderfuldestruction
files
👍
1
2
#1 opened 4 days ago
by
avidwriter
Baseline better
👍
1
1
#1 opened 4 days ago
by
wonderfuldestruction
Feedback from running in LM Studio 0.39.3 with v1.103.2 of llama.cpp
29
#1 opened 18 days ago
by
spanspek
Infinite loop
1
#2 opened 9 days ago
by
kielCAC
Tried to use with llama-cpp-python without success
1
#1 opened 11 days ago
by
rriscoc
really underrated
👍
2
1
#2 opened 14 days ago
by
frekvensnord
Would it make sense to get Qwen3-VL MXFP4 quants?
11
#2 opened 18 days ago
by
ampersandru
Feedback from testing
👍
1
1
#1 opened 16 days ago
by
spanspek
Re-cooking imatrix and quants with updated ik/llama.cpp PR
🚀
1
14
#1 opened 17 days ago
by
ubergarm
is this model still can use 1M context window or not?
1
#1 opened 20 days ago
by
Slach
surprising performance, thx!
3
#2 opened 30 days ago
by
dexgeh
Can´t load the model
1
#3 opened about 1 month ago
by
jpsequeira
such a cool qunat mate
1
#1 opened about 1 month ago
by
gopi87