ManniX PRO
ManniX-ITA
AI & ML interests
None yet
Recent Activity
new activity about 5 hours ago
ManniX-ITA/gemma-4-A4B-98e-v7-coder-it-GGUF:Gets stuck in loops using llama.cpp updated a model about 15 hours ago
ManniX-ITA/gemma-4-A4B-98e-v7-coderx-it updated a model about 15 hours ago
ManniX-ITA/gemma-4-A4B-98e-v7-coder-itOrganizations
None yet
Gemma 4 dense (non-MoE) variants — 31B head-prune + quants.
Qwen 3.5 merges & prunes — 27B Omnimerge + 4B MicroCoder line.
-
ManniX-ITA/Qwen3.6-27B-A3B-Coder-MTP-GGUF
Text Generation • 26B • Updated • 42.9k • 18 -
ManniX-ITA/Qwen3.6-27B-A3B-Coder
Text Generation • 27B • Updated • 499 • 4 -
ManniX-ITA/Qwen3.6-27B-Omnimerge-v4-GGUF
Image-Text-to-Text • 27B • Updated • 3.89k • 35 -
ManniX-ITA/Qwen3.6-27B-Omnimerge-v4
Image-Text-to-Text • 28B • Updated • 28 • 14
Gemma 4 speculative-decoding / MTP assistant drafter heads.
-
ManniX-ITA/Qwen3.6-27B-A3B-Coder-MTP-GGUF
Text Generation • 26B • Updated • 42.9k • 18 -
ManniX-ITA/Qwen3.6-27B-A3B-Coder
Text Generation • 27B • Updated • 499 • 4 -
ManniX-ITA/Qwen3.6-27B-Omnimerge-v4-GGUF
Image-Text-to-Text • 27B • Updated • 3.89k • 35 -
ManniX-ITA/Qwen3.6-27B-Omnimerge-v4
Image-Text-to-Text • 28B • Updated • 28 • 14
Gemma 4 dense (non-MoE) variants — 31B head-prune + quants.
Gemma 4 speculative-decoding / MTP assistant drafter heads.
Qwen 3.5 merges & prunes — 27B Omnimerge + 4B MicroCoder line.