-
LiquidAI/LFM2-1.2B-RAG-GGUF
Text Generation • 1B • Updated • 2.03k • 70 -
warmachine68/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-nasty_feline_mule
Text Generation • 0.5B • Updated • 27 • 1 -
WeiboAI/VibeThinker-3B
Text Generation • 3B • Updated • 2.84k • • 865 -
darkc0de/XortronCriminalComputingConfig-i1-GGUF
24B • Updated • 1.57k • 12
🔄 In a Training Loop
"Kapha"
kapha
AI & ML interests
Q2 is for sh*ts and giggles
Q4 is for the desperate
Q6 is for the average
Q8 you're trying harder good for you
Those who say that "NOW YOU CAN RUN AI LOCALLY EVEN IF YOU HAVE 4.5 VRAM" and then show a 4.7 gigs model at Q2 should absolutely step on legos for the rest of their scammy lives.
PS: if you are looking for good advice, you're not gonna find it here.
Recent Activity
liked a model about 6 hours ago
nightmedia/Qwen3.5-9B-Brainwaves-DeepThought-STEM-OneJev1.6 new activity about 6 hours ago
slmconsortium/README:New Member Ratification: ray0rf1re new activity about 6 hours ago
mradermacher/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-i1-GGUF:lm studio上面加载失败,无法使用,模型里缺乏mtp