Hopefully you will get some love from llama.cpp and unsloth. That will make it consumer hardware friendly to try.
Tipu Sultan
engrtipusultan
AI & ML interests
None yet
Recent Activity
new activity
1 day ago
datalab-to/chandra:Urdu support?
new activity
1 day ago
noctrex/Chandra-OCR-GGUF:Thank you. Any experience?
new activity
5 days ago
lightonai/LightOnOCR-1B-1025:Run with llamacpp
Organizations
None yet
Urdu support?
#2 opened 1 day ago
by
engrtipusultan
Thank you. Any experience?
1
#1 opened 1 day ago
by
engrtipusultan
Run with llamacpp
â¤ď¸
đĽ
2
6
#4 opened 6 days ago
by
AbacusGauge
output endless <ecel>
1
#42 opened 16 days ago
by
openmartin
Missing MTP layers, add it again please!
đ
2
22
#1 opened 13 days ago
by
TheDrummer
IQ4_XS fits 64G mac when set max vram to 61440
1
#1 opened 10 days ago
by
CoruNethron
Much worse than old model on llama.cpp
#11 opened 10 days ago
by
engrtipusultan
llama.cpp recommended sampling parameters
#4 opened 12 days ago
by
engrtipusultan
GGUF
1
#1 opened 12 days ago
by
engrtipusultan
llama.cpp example
1
#1 opened 13 days ago
by
engrtipusultan
llama.cpp support
1
#1 opened 18 days ago
by
engrtipusultan
Failed to load CLIP
2
#1 opened 27 days ago
by
engrtipusultan
Unable to OCR
#3 opened 26 days ago
by
engrtipusultan
Is it thinking or instruct?
1
#1 opened 27 days ago
by
engrtipusultan
ONNX Conversion Available - Performance Benchmarks & Implementation Guide
đ
â¤ď¸
2
7
#32 opened about 1 month ago
by
glamberson
More Information
đ
1
#1 opened about 1 month ago
by
engrtipusultan
llama.cpp quants
1
#4 opened about 1 month ago
by
engrtipusultan
model has unused tensor on UD-IQ2_M: Is it normal?
đ
1
#12 opened about 1 month ago
by
engrtipusultan
llama.cpp
â
2
4
#16 opened about 1 month ago
by
engrtipusultan