Dan Simmonds
BingoBird
AI & ML interests
Hobbyist, SD, LLM
Recent Activity
liked a model about 3 hours ago
bartowski/granite-4.2-30b-GGUF new activity 2 days ago
deepseek-ai/DeepSeek-V4-Flash-0731:<3 to deepseek team.... new activity 2 days ago
unsloth/DeepSeek-V4-Flash-0731-GGUF:2x3090 Mixed GPU/CPU inference: -fit on and all good!Organizations
None yet
<3 to deepseek team....
❤️🤗 18
1
#34 opened 23 days ago
by
nonmairub
2x3090 Mixed GPU/CPU inference: -fit on and all good!
#42 opened 16 days ago
by
BingoBird
So is this like, for you and your friends or...
1
#1 opened 3 days ago
by
BingoBird
Issues encountered when deploying UD-Q8_K_XL
5
#44 opened 13 days ago
by
dw1932
Excellent quality
1
#1 opened 11 days ago
by
Tuipveus
DAE know how to corretly run DSpark with part of the model offloaded to RAM using llama.cpp?
3
#40 opened 17 days ago
by
LukeC110
Error: not a valid gguf file: not starting with GGUF magic number
2
#12 opened about 1 month ago
by
Obscurion
New activity in drowzeys/keys-DeepSeekV4-Flash-GA-0731-Dspark-Abliterated-Anchored-Tensors 5 days ago
Coding Evaluation
#6 opened 5 days ago
by
BingoBird
500K context c1 87 tok/s c4 156 tok/s aggregate --- dual sparks. Thank you!!!
1
#2 opened 21 days ago
by
WinWinCyber
Huge Thanks
#1 opened 5 days ago
by
BingoBird
DSpark enables DeepSeek to run 2x Faster!
❤️🔥 2
5
#36 opened 20 days ago
by
danielhanchen
Join the Discord server!
2
#3 opened 8 days ago
by
HauhauCS
6 months later - Still the one!
❤️ 1
#8 opened 14 days ago
by
BingoBird
Great Project!!
#2 opened 20 days ago
by
BingoBird
Request: K128 (128 experts) REAP variant for single 96GB GPU
2
#1 opened 21 days ago
by
mrwd2005
Thank you for making these.
🚀❤️ 4
1
#1 opened 21 days ago
by
BingoBird
Dual RTX3090 and 64GB DDR4 + 78GB Swap. Speed: ~1.78 TPS
🤝👍 4
15
#8 opened 25 days ago
by
robert1968
So much expectations from a small model
5
#1 opened 2 months ago
by
hamadfx
Getting better speeds and somehow results then Qwen3.6-35B-A3B! Q4
👍 1
2
#15 opened about 2 months ago
by
SaturnsVoid