Hannes Geist
hgeist
AI & ML interests
None yet
Recent Activity
new activity 3 days ago
unsloth/Qwen3.8-Flash-Next-GGUF:Too slow in 2 x H100, got decode 40t/s new activity 12 days ago
unsloth/Qwen3.8-Flash-Next-GGUF:MTP support in Q4 ? new activity 12 days ago
unsloth/Qwen3.8-Flash-Next-GGUF:Tested on RTX5070TI 16GB VRAM: 20 t/sOrganizations
Too slow in 2 x H100, got decode 40t/s
3
#60 opened 5 days ago
by
tientitmu
MTP support in Q4 ?
👍 3
5
#21 opened 13 days ago
by
dpachong
Tested on RTX5070TI 16GB VRAM: 20 t/s
👀👍 10
11
#24 opened 12 days ago
by
WhiteDan64
Thinking Nightmare
🧠 2
10
#27 opened 12 days ago
by
WhiteDan64
Vision
👀 1
9
#19 opened 13 days ago
by
hgeist
can you please make a 39b dense model?
4
#23 opened 13 days ago
by
Manni1000
here qwen3.8-flash-next is 125B but unsloth has 180B ... how come?
3
#17 opened 13 days ago
by
mayankiit04
Excessive CoT verbosity on simple, well-defined tasks
9
#5 opened 20 days ago
by
desugar
Removed Vision Capabilities
3
#7 opened 19 days ago
by
tushar310
Not for coding?
👀👍 4
3
#6 opened 19 days ago
by
auf1r2
MTP Support
🚀 9
2
#2 opened 20 days ago
by
DefaultDF
wen on artificialanalysis.ai?
6
#2 opened 20 days ago
by
anvme
EPIC ! Thank you! Thank you very much! CHINA!
🚀❤️ 17
2
#44 opened 25 days ago
by
RomanHammer
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF about 2 months ago
"Pelican Test" ... wtf is this shit?
13
#14 opened about 2 months ago
by
CurbStomper
It doesn't think
4
#1 opened about 2 months ago
by
hgeist
Do the numbers differ from Ornith and Qwen graphs?
➕ 1
11
#1 opened about 2 months ago
by
hgeist
SWE bench + DeepSWE?
7
#1 opened about 2 months ago
by
hgeist
I will kiss you if Grug survives SWE-bench
❤️ 1
2
#2 opened about 2 months ago
by
Magyarmex
gguf
➕ 5
4
#1 opened about 2 months ago
by
Tapka