Muthukumaran N M
mechanicmuthu
AI & ML interests
llama.cpp, privateGPT, langchain
Recent Activity
new activity
about 15 hours ago
ubergarm/DeepSeek-V3-0324-GGUF:Expected speed in some known hardware - data required
liked
a model
about 15 hours ago
ubergarm/DeepSeek-V3-0324-GGUF
new activity
6 days ago
unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF:<think></think>
Organizations
None yet
mechanicmuthu's activity
Expected speed in some known hardware - data required
1
#1 opened about 15 hours ago
by
mechanicmuthu
<think></think>
5
#3 opened 2 months ago
by
sn3d9
Can it run on CPU?
#1 opened 13 days ago
by
mechanicmuthu
Request for uploading similar AWQ GGUF file for Solar Instruct 10.7B
#1 opened over 1 year ago
by
mechanicmuthu
Demo does not provide outputs for similarity score
#2 opened over 1 year ago
by
mechanicmuthu
Request to create one Q8_0 version with --leave-output-tensor
#1 opened over 1 year ago
by
mechanicmuthu
Cosine Similarity is always HIGH
5
#7 opened over 1 year ago
by
artificialgenerations4gsdfg
Need any help?
3
#2 opened over 1 year ago
by
hunkim
Damn exciting this is!
1
#1 opened over 1 year ago
by
mechanicmuthu
GGMLv3 is lightning fast
1
#2 opened almost 2 years ago
by
mechanicmuthu
2-bit models... Wow.
1
#1 opened almost 2 years ago
by
mechanicmuthu
Which version v3?
1
#1 opened almost 2 years ago
by
mechanicmuthu
GGMLv3 is lightning fast
1
#2 opened almost 2 years ago
by
mechanicmuthu