Rat
WetRat
Β·
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
meituan-longcat/LongCat-Video-Avatar-1.6 liked a model 4 days ago
MiniMaxAI/MiniMax-H3-Image liked a model 16 days ago
nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GBOrganizations
None yet
4.05 / 3.05 work nicely, 2.05 loops at "max" reasoning
#3 opened 30 days ago
by
WetRat
Confused about the differences vs Unsloth GGUFs
1
#1 opened 2 months ago
by
WetRat
Any ETA on the 5bit quants?
π 2
2
#7 opened 3 months ago
by
JPFlare
Potential issue with Q8? (nevermind; the issue was on my side only)
2
#1 opened 3 months ago
by
WetRat
A few more tics to fight off (not Scotoma-2 specific; pure Gemma 4 stuff).
4
#1 opened 3 months ago
by
WetRat
Thank you! πΉ
β€οΈ 7
10
#1 opened 4 months ago
by
McG-221
DeepSeek-V4-Flash is now ready to run locally! π³
β€οΈπ 8
19
#6 opened 4 months ago
by
danielhanchen
Worse than (smaller) MiniMax M2.7??
17
#2 opened 7 months ago
by deleted
Will there be a smaller model like Qwen3.5 122 or Nemotron 3 super
β 7
7
#9 opened 7 months ago
by
mayankiit04
General observation concerning Gemma 4 in RP (highly relevant to the case)
9
#1 opened 7 months ago
by
WetRat
βThe doom lies in yourself, not in your name.β
π 7
537
#15 opened about 1 year ago
by
jukofyork
[Q3KM] Seems to be functioning, would love to see more quants.
π 2
12
#1 opened 7 months ago
by
AutisticPancake
[Q3KM] Seems to be functioning, would love to see more quants.
π 2
12
#1 opened 7 months ago
by
AutisticPancake
[Q3KM] Seems to be functioning, would love to see more quants.
π 2
12
#1 opened 7 months ago
by
AutisticPancake