Bartowski PRO
bartowski
AI & ML interests
Research Engineer at arcee.ai
Official model curator for https://lmstudio.ai/
Recent Activity
published
a model
about 4 hours ago
bartowski/prithivMLmods_Viper-Coder-32B-Elite13-GGUF
updated
a model
about 4 hours ago
bartowski/prithivMLmods_Viper-Coder-32B-Elite13-GGUF
new activity
about 6 hours ago
lmstudio-community/c4ai-command-a-03-2025-GGUF:LMS Q4KM only 16k Context
Organizations
bartowski's activity
LMS Q4KM only 16k Context
3
#1 opened about 10 hours ago
by
JJ404GO
Can't run in llama.cpp, wrong tensor shape
6
#1 opened about 10 hours ago
by
bartowski

Q6_K vs Q6_K_L
6
#1 opened 1 day ago
by
mahdisml

Does Ollama support vision features?
4
#2 opened 1 day ago
by
YarvixPA
Bartowski! 0.0!!!! You are on double-secret probation for this jinja error!
7
#4 opened 8 days ago
by
rkh661

Fails to load the model in LM Studio
1
#1 opened 1 day ago
by
AManev
Failed to load model
4
#1 opened 2 days ago
by
VivekLeon
Cannot load this model in Mac mini
1
#1 opened 1 day ago
by
zletpm
Jinja/auto template broken. // temp fix using Llama 3 template.
5
#9 opened 2 days ago
by
DavidAU

REALLY slow with flash attention and quantized cache.
7
#2 opened 2 days ago
by
Olafangensan
Prompt template
13
#1 opened 3 days ago
by
YearZero
<sep> not a special token?
3
#4 opened 3 days ago
by
bartowski

can't quantize it to f16
8
#4 opened 5 days ago
by
owao
Wur doomed!
108
#14 opened about 1 month ago
by
jukofyork

Please make i1 quants of my latest 72b model
18
#1 opened 22 days ago
by
rombodawg

Measuring quantization error
1
#3 opened 4 days ago
by
ddh0

Wowowowow
27
#1 opened 9 days ago
by
owao
Different than Unsloth?
4
#8 opened 6 days ago
by
MrDevolver

safetensors format?
1
#1 opened 6 days ago
by
pdrolet