Rio Grande
dandandelion
AI & ML interests
None yet
Recent Activity
liked a model about 6 hours ago
tencent/Hy4-flash liked a model about 13 hours ago
apple/FastFrames-LOrganizations
None yet
Speed notes: UD-IQ1_S on a 64 GB RAM + 16 GB card PC, about 11.5 tok/s in llama.cpp
1
#16 opened 7 days ago
by
aradzombie
Wonderful
❤️ 1
4
#1 opened 26 days ago
by
hamzah0asadullah
Ampere?
3
#6 opened 4 days ago
by
dandandelion
Requesting ComfyUI GGUF, thank you!
6
#2 opened 8 days ago
by
yah4
IQ3_XXS is insane and probably the best size to quality ratio
🔥🤗 9
5
#102 opened 9 days ago
by
dandandelion
I’m a believer
👍➕ 3
17
#43 opened 16 days ago
by
fdsljwre
Just a little benchmark of reasoning
🧠🤯 10
1
#4 opened 16 days ago
by
dandandelion
Language Broken === Model Broken
1
#27 opened 22 days ago
by
ebuwiz
How to use the Coder-L in Strata (Windows) using AMD?
❤️ 1
8
#7 opened 24 days ago
by
soyalemujica
Able to run the L version with 2gigs free and full context/history. Thank you!
🔥❤️ 1
3
#10 opened 21 days ago
by
SeattleSysop
Benchmaxxed
😔 1
15
#22 opened 23 days ago
by
rekillkos
Nanbeige 4.3 33B - HAS NO VISION - How are you suppose to use this for WEB DEV?
👍 2
3
#21 opened 23 days ago
by
akierum
can it run in 2 kilobyte
4
#16 opened 26 days ago
by
erorajdm
Good job on this frankenmodel!
#6 opened 23 days ago
by
dandandelion
how do these deepseek Quants measure against IQ3_S Qwen3.8-flash-next RCO GSK
👍 1
7
#4 opened 26 days ago
by
mayankiit04
Unbelievable performance improvements on v2.6! (Overthinking issue fixed)
🔥 7
3
#5 opened 26 days ago
by
aidinmc
how to run DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF on 128gb mac?
2
#7 opened 25 days ago
by
fut888
How many tokens will there be
👀 1
8
#6 opened 25 days ago
by
chichas
IQ2_XS vs IQ2XXS - why recommend the smaller one?
👍 6
7
#3 opened 26 days ago
by
spanspek
IQ3_S is pretty much BF16
👍🚀 5
9
#32 opened about 2 months ago
by
dandandelion