ggml-org/gemma-4-12B-GGUF
Any-to-Any • 12B • Updated • 1.32k • 2
Ben Kelly PRO
YellowjacketGames
AI & ML interests
None yet
Recent Activity
liked a model 1 day ago
ggml-org/gemma-4-12B-GGUF liked a model 1 day ago
nivvis/Qwen3.5-9B-EQ-v5.1-GGUF liked a model 7 days ago
unsloth/Qwen3.5-4B-GGUFOrganizations
liked 2
models 1 day ago
liked a
model 7 days ago
We use Fishaudio already and are curious about this
3
#6 opened 10 days ago
by YellowjacketGames
liked a
model 15 days ago
updated a
collection 15 days ago
replied to danielhanchen's post 15 days ago
That's almost exactly what I'm estimating based on Deepseek R1 pulling about 1 or 2 TPS. Offloading a few layers to some A6000s didnt really help much either.
replied to danielhanchen's post 15 days ago
I have enough DDR4 to put this on a 64 core threadripper, but I'm worried about how brutally slow it will be :)
liked a
Space 28 days ago
why AGPL?
#1 opened about 2 months ago
by YellowjacketGames
upvoted a collection about 2 months ago
liked a
model about 2 months ago
updated a
collection 3 months ago
liked a
model 3 months ago
updated a
collection 3 months ago
liked a
model 3 months ago
commented on Flux 2 Dev on a single RTX A6000 48gb GPU # 3 months ago
btw we got it using 2 nvlinked RTX 6000 GPUs and its even better.
Interested in training this further myself
#1 opened 3 months ago
by YellowjacketGames
liked 2
models 3 months ago
