-
caiovicentino1/Qwopus3.5-9B-v3-PolarQuant-Q5
Text Generation • 9B • Updated • 2.37k • 8 -
caiovicentino1/Gemma-4-E4B-it-PolarQuant-Multi
Any-to-Any • Updated • 255 • 1 -
caiovicentino1/Qwopus3.5-9B-v3-PolarQuant-MLX-4bit
Text Generation • 1B • Updated • 1.58k • 6 -
caiovicentino1/Huihui-Qwopus3.5-27B-v3-abliterated-PolarQuant-Q5
Text Generation • 26B • Updated • 2.05k • 10
Meeeee
olivermee11
AI & ML interests
None yet
Recent Activity
liked a model 6 days ago
caiovicentino1/Qwopus3.5-9B-v3-PolarQuant-Q5 updated a collection 6 days ago
PolarQuant? updated a collection 6 days ago
PolarQuant?Organizations
None yet
Models tested and running on M1 Pro 16GB Mac. GGUF via llama.cpp + LM Studio, MLX via mlx-lm.
-
google/gemma-4-E4B-it
Any-to-Any • 8B • Updated • 1.27M • 595 -
HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Image-Text-to-Text • 8B • Updated • 432k • 271 -
HauhauCS/Gemma-4-E2B-Uncensored-HauhauCS-Aggressive
Image-Text-to-Text • 5B • Updated • 130k • 88 -
Jackrong/Qwopus3.5-9B-v3-GGUF
Image-Text-to-Text • 9B • Updated • 105k • 253
Jackrong Claude Opus reasoning distils (Qwopus) and HauhauCS uncensored/obliterated models.
-
Jackrong/Qwopus3.5-9B-v3-GGUF
Image-Text-to-Text • 9B • Updated • 105k • 253 -
Jackrong/Qwopus3.5-4B-v3-GGUF
Image-Text-to-Text • 4B • Updated • 22.1k • 31 -
Jackrong/Qwopus3.5-27B-v3-GGUF
Image-Text-to-Text • 27B • Updated • 118k • 272 -
HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Image-Text-to-Text • 8B • Updated • 432k • 271
Models running on Oracle Cloud Free Tier ARM64 (4x Neoverse-N1, 24GB RAM, CPU-only) via llama.cpp. Real-world tested list for Oracle free tier.
-
caiovicentino1/Qwopus3.5-9B-v3-PolarQuant-Q5
Text Generation • 9B • Updated • 2.37k • 8 -
caiovicentino1/Gemma-4-E4B-it-PolarQuant-Multi
Any-to-Any • Updated • 255 • 1 -
caiovicentino1/Qwopus3.5-9B-v3-PolarQuant-MLX-4bit
Text Generation • 1B • Updated • 1.58k • 6 -
caiovicentino1/Huihui-Qwopus3.5-27B-v3-abliterated-PolarQuant-Q5
Text Generation • 26B • Updated • 2.05k • 10
Jackrong Claude Opus reasoning distils (Qwopus) and HauhauCS uncensored/obliterated models.
-
Jackrong/Qwopus3.5-9B-v3-GGUF
Image-Text-to-Text • 9B • Updated • 105k • 253 -
Jackrong/Qwopus3.5-4B-v3-GGUF
Image-Text-to-Text • 4B • Updated • 22.1k • 31 -
Jackrong/Qwopus3.5-27B-v3-GGUF
Image-Text-to-Text • 27B • Updated • 118k • 272 -
HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Image-Text-to-Text • 8B • Updated • 432k • 271
Models tested and running on M1 Pro 16GB Mac. GGUF via llama.cpp + LM Studio, MLX via mlx-lm.
-
google/gemma-4-E4B-it
Any-to-Any • 8B • Updated • 1.27M • 595 -
HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Image-Text-to-Text • 8B • Updated • 432k • 271 -
HauhauCS/Gemma-4-E2B-Uncensored-HauhauCS-Aggressive
Image-Text-to-Text • 5B • Updated • 130k • 88 -
Jackrong/Qwopus3.5-9B-v3-GGUF
Image-Text-to-Text • 9B • Updated • 105k • 253
Models running on Oracle Cloud Free Tier ARM64 (4x Neoverse-N1, 24GB RAM, CPU-only) via llama.cpp. Real-world tested list for Oracle free tier.