Dan Simmonds
BingoBird
AI & ML interests
Hobbyist, SD, LLM
Recent Activity
liked a model 2 days ago
mradermacher/Llama-3.2-3B-Instruct-uncensored-GGUF liked a model 2 days ago
wave-on-discord/silly-v0.2 liked a model 2 days ago
mradermacher/OpenAI-gpt-oss-20B-INSTRUCT-Terse-Heretic-Uncensored-GGUFOrganizations
None yet
6 months later - Still the one!
❤️ 1
#8 opened 7 days ago
by
BingoBird
Mixed GPU/CPU inference: WHICH LAYERS TO PIN TO GPU?
#42 opened 8 days ago
by
BingoBird
Great Project!!
#2 opened 13 days ago
by
BingoBird
Request: K128 (128 experts) REAP variant for single 96GB GPU
2
#1 opened 13 days ago
by
mrwd2005
Thank you for making these.
🚀❤️ 3
1
#1 opened 14 days ago
by
BingoBird
Dual RTX3090 and 64GB DDR4 + 78GB Swap. Speed: ~1.78 TPS
🤝👍 4
15
#8 opened 18 days ago
by
robert1968
So much expectations from a small model
5
#1 opened about 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
Having `encoding` problem with bash commands and paths all the way...
1
#20 opened about 2 months ago
by
gbuzhf
Aider Polyglot Benchmark Results (C++ & Python) — Q4 through Q8
👍 4
5
#23 opened about 2 months ago
by
YukiTomita-CC
Ornith refused to carry out the order, saying it was against the law.
2
#43 opened about 1 month ago
by
Marlanwong
Could this be a LoRA?
#1 opened 16 days ago
by
BingoBird
UD-IQ4_XS 137 GB or UD-IQ4_NL 137 GB?
👀 2
#25 opened 16 days ago
by
BingoBird
Thank you so much, asking about model performance
4
#1 opened 16 days ago
by
MahouOfficial
<3 <3 <3
❤️ 3
1
#2 opened 18 days ago
by
nonmairub
26B?
5
#2 opened 2 months ago
by
FrenzyBiscuit
KLD Benchmarks + why Q8_K_XL vs MXFP4 naming
❤️👍 11
6
#11 opened 18 days ago
by
danielhanchen
Run DeepSeek-V4-Flash-0731 in Unsloth! 🦥♥️
👍🔥 16
8
#6 opened 18 days ago
by
danielhanchen
Lossless UD-Q8_K_XL. UD-Q4_K_XL also provided for now
❤️🔥 15
10
#2 opened 18 days ago
by
danielhanchen