Qwen/Qwen3.8-2.4T-A95B
Text Generation • 2.4T • Updated • 3.83k • • 900
📓 Merging AI models
Vasko Djack
Akahsizrr
AI & ML interests
ML eng, learning everyday.
Working on 2 new AI training pipelines, and a model merging architecture for frontier specialized local models.
Recent Activity
liked a model about 4 hours ago
Qwen/Qwen3.8-2.4T-A95B liked a model about 8 hours ago
Qwen/Qwen3.8-27B new activity about 19 hours ago
Akahsizrr/fuse-1-Lite:Any benchmark comparisons with similarly sized models?Organizations
liked a
model about 4 hours ago
liked a
model about 8 hours ago
Any benchmark comparisons with similarly sized models?
3
#3 opened 2 days ago
by 
miifanboy
are we there yet?
6
#1 opened 3 days ago
by 
pirola
updated a
dataset 3 days ago
published a
dataset 3 days ago
liked a
model 3 days ago
updated a
model 3 days ago
published a
model 3 days ago
is it usable?
10
#1 opened 6 days ago
by pirola
liked 3
models 4 days ago
updated 2
models 5 days ago
liked a
model 7 days ago
any plan to merge to official llama.cpp
1
#2 opened 8 days ago
by 
FM-1976
Integration issue
1
#3 opened 7 days ago
by 
DarkKitsune
tokenizer
2
#2 opened 8 days ago
by 
cnmoro
where Q4_K_M?
1
#1 opened 8 days ago
by 
holooo