Hannes Geist
hgeist
AI & ML interests
None yet
Recent Activity
new activity about 3 hours ago
Qwen/Qwen3.8-Flash-Next:can you please make a 39b dense model? new activity about 3 hours ago
unsloth/Qwen3.8-Flash-Next-GGUF:MTP support in Q4 ? new activity about 5 hours ago
unsloth/Qwen3.8-Flash-Next-GGUF:VisionOrganizations
can you please make a 39b dense model?
3
#23 opened about 3 hours ago
by
Manni1000
MTP support in Q4 ?
👍 1
2
#21 opened about 3 hours ago
by
dpachong
Vision
👀 1
3
#19 opened about 5 hours ago
by
hgeist
here qwen3.8-flash-next is 125B but unsloth has 180B ... how come?
2
#17 opened about 8 hours ago
by
mayankiit04
Excessive CoT verbosity on simple, well-defined tasks
9
#5 opened 7 days ago
by
desugar
Removed Vision Capabilities
3
#7 opened 7 days ago
by
tushar310
Not for coding?
👀👍 4
3
#6 opened 7 days ago
by
auf1r2
MTP Support
🚀 9
2
#2 opened 7 days ago
by
DefaultDF
wen on artificialanalysis.ai?
6
#2 opened 7 days ago
by
anvme
EPIC ! Thank you! Thank you very much! CHINA!
🚀❤️ 17
2
#44 opened 12 days ago
by
RomanHammer
New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF about 1 month ago
"Pelican Test" ... wtf is this shit?
13
#14 opened about 1 month ago
by
CurbStomper
It doesn't think
4
#1 opened about 1 month ago
by
hgeist
Do the numbers differ from Ornith and Qwen graphs?
➕ 1
11
#1 opened about 1 month ago
by
hgeist
SWE bench + DeepSWE?
7
#1 opened about 1 month ago
by
hgeist
I will kiss you if Grug survives SWE-bench
❤️ 1
2
#2 opened about 1 month ago
by
Magyarmex
gguf
➕ 5
4
#1 opened about 1 month ago
by
Tapka
Garbled response from Q8_0
4
#3 opened about 2 months ago
by
cnsiva
The 9B MTP Q4_K_M model is looping its reasoning
👍 2
9
#17 opened about 2 months ago
by
bakaemon
Request: Please quantisize qwen3.6 27B and 35B with MTP please
🔥 3
5
#10 opened 4 months ago
by
hgeist