Ljubomir Josifovski
ljupco
AI & ML interests
Now - ML/AI, agents, auto-science & engineering, forecasting. Previous - systematic trading, research & development. Previous^2 - speech recognition in noise, speech synthesis, machine learning.
Recent Activity
liked a model about 8 hours ago
rapid-mlx/Qwen3.8-Flash-Next-4bit liked a model 1 day ago
alesha-pro/Qwen3.8-27B-S-mirai-GGUF liked a model 2 days ago
unsloth/embeddinggemma-2-GGUFOrganizations
None yet
doh - moespresso: MoEspresso requires macOS 26.2 or later. :-(
😔 1
1
#1 opened about 2 months ago
by ljupco
llama.cpp supports?
👍👀 16
9
#4 opened 2 months ago
by 
cimilarkes
llamma.cpp support
👍 12
5
#2 opened 2 months ago
by 
RandomUserNA12312
Ling-3.0-flash?
➕ 2
#9 opened 3 months ago
by ljupco
Runs on M2 Max too
#1 opened 5 months ago
by ljupco
thank you! - running on llama.cpp on M2 Max now :-)
❤️🤗 2
1
#8 opened 5 months ago
by ljupco
GGUF quants and llama.cpp inference?
#7 opened 8 months ago
by ljupco
mlx-lm not ready
👍 5
12
#1 opened about 1 year ago
by 
Weiguo
🚀 Best Practices for Evaluating the Qwen3-Next Model
🚀👍 7
1
#8 opened about 1 year ago
by 
Yunxz
How does this compare to other "1M context"-s UloRL and Unsloth?
#5 opened about 1 year ago
by ljupco
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma3n'
2
#3 opened over 1 year ago
by ljupco
provide int4 version pls
👀➕ 2
4
#2 opened over 1 year ago
by 
Josh1026
Is there any documentation about the sampling parameters maybe?
1
#1 opened over 1 year ago
by ljupco
Please share feedback here!
34
#6 opened over 1 year ago
by 
shimmyshimmer
Please share feedback here!
34
#6 opened over 1 year ago
by shimmyshimmer
Please share feedback here!
34
#6 opened over 1 year ago
by shimmyshimmer