Martin Makuch
McUH
AI & ML interests
None yet
Recent Activity
new activity
about 1 month ago
google/gemma-3-27b-it-qat-q4_0-gguf:why is the size bigger than regular Q4_0 quants ?
new activity
about 2 months ago
bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF:Does it support thinking on/off?
new activity
3 months ago
Steelskull/L3.3-Damascus-R1:No reasoning
Organizations
None yet
McUH's activity
why is the size bigger than regular Q4_0 quants ?
3
6
#1 opened about 1 month ago
by
lefromage
Does it support thinking on/off?
5
#2 opened about 2 months ago
by
CHNtentes
No reasoning
6
#1 opened 3 months ago
by
abiteddie
<thinking> is the proper tag?
1
4
#8 opened 3 months ago
by
McUH
IQ3_XS quant not visible in sidebar
11
#1 opened 3 months ago
by
x0wllaar

Maybe a name change?
4
2
#1 opened 4 months ago
by
Olafangensan
Observation: 4-bit quantization can't answer the Strawberry prompt
1
12
#2 opened 7 months ago
by
ThePabli
RP Input Example?
1
#1 opened 7 months ago
by
lazyDataScientist

higher quant
1
5
#1 opened 8 months ago
by
McUH
Works good generating python on my 64GB RAM w/ 3090TI 24GB VRAM dev box
2
3
#2 opened 10 months ago
by
ubergarm