Frontier and off-beat releases I track — language world models, persona merges and experimental abliterated fine-tunes.
Stéphane FERREIRA PRO
Ferr0
AI & ML interests
Infra-minded AI builder — local LLM inference (Ollama / vLLM on a home RTX 3090), structured generation & tool-calling, offline RAG, and defensive AI security. Self-hostable, reproducible demos.
Recent Activity
liked a model 2 days ago
tvall43/Qwen3.6-14B-A3B-FableVibes-GGUF liked a model 2 days ago
DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF liked a model 3 days ago
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUFOrganizations
None yet
Tool-calling LLMs I run on one RTX 3090 to operate my homelab — agentic coding, log triage and infra automation over MCP.
-
Qwen/Qwen3-Coder-30B-A3B-Instruct
Text Generation • 31B • Updated • 1.53M • • 1.18k -
deepreinforce-ai/Ornith-1.0-9B
Text Generation • 1.47M • Updated • 1.68M • • 489 -
google/gemma-4-12B-it
Any-to-Any • 12B • Updated • 2.98M • 1.35k -
Salesforce/xlam-function-calling-60k
Viewer • Updated • 60k • 11.1k • 662
Frontier and off-beat releases I track — language world models, persona merges and experimental abliterated fine-tunes.
Tool-calling LLMs I run on one RTX 3090 to operate my homelab — agentic coding, log triage and infra automation over MCP.
-
Qwen/Qwen3-Coder-30B-A3B-Instruct
Text Generation • 31B • Updated • 1.53M • • 1.18k -
deepreinforce-ai/Ornith-1.0-9B
Text Generation • 1.47M • Updated • 1.68M • • 489 -
google/gemma-4-12B-it
Any-to-Any • 12B • Updated • 2.98M • 1.35k -
Salesforce/xlam-function-calling-60k
Viewer • Updated • 60k • 11.1k • 662
models 0
None public yet
datasets 0
None public yet