John Leimgruber III
ubergarm
AI & ML interests
Open LLMs and Astrophotography image processing.
Recent Activity
updated
a model
about 3 hours ago
ubergarm/DeepSeek-V3.1-GGUF
new activity
about 4 hours ago
ubergarm/DeepSeek-V3.1-GGUF:quant req: 256 GB RAM + 96 GB VRAM
updated
a model
about 6 hours ago
ubergarm/Qwen3-Coder-30B-A3B-Instruct-GGUF
Organizations
None yet
quant req: 256 GB RAM + 96 GB VRAM
👍
1
18
#1 opened 3 days ago
by
whoisjeremylam
THIS WORKS SO WELL on a 10 year old PC
🔥
1
3
#3 opened 1 day ago
by
nisten
a few questions
1
#3 opened 1 day ago
by
lmganon123
Hybrid inference speed tests
👍
1
10
#7 opened 6 days ago
by
Doctor-Shotgun
testing
👍
1
5
#2 opened 2 days ago
by
shewin
Which convert_bf16_to_gguf.py did you use?
1
#1 opened 3 days ago
by
ubergarm
gguf when??? cmon guys, where is bartowski?!
20
#1 opened 3 days ago
by
Hanswalter
gguf when? cmon, its been 11 min already!
🔥
5
24
#2 opened 5 days ago
by
Hanswalter
Any chance for an IQ3_K?
👍
2
18
#6 opened 15 days ago
by
original-el8
KL Divergence as Performance Metric
1
#5 opened 6 days ago
by
joaquinrfs
Can you provide some low-precision quantization options?
➕
👍
3
11
#3 opened 20 days ago
by
lingyezhixing
Good job
56
#2 opened 20 days ago
by
huccjj
Mix for 96gb ram
10
#15 opened 2 months ago
by
nu-x
IQ4 on Mac
7
#7 opened 8 days ago
by
bibproj
The same or nah?
3
#27 opened 11 days ago
by
sdfasdfasdfsdfsdf
270m?
❤️
😎
19
1
#1 opened 10 days ago
by
ubergarm
Thank you
❤️
1
8
#10 opened 16 days ago
by
alain401
Not compatible with GGUF
👍
2
3
#1 opened 14 days ago
by
ruleez
ComfyUI LoRA Loader Support?
🔥
4
9
#1 opened 18 days ago
by
ubergarm
Performance? Methodology?
5
#2 opened 15 days ago
by
lightenup