Infrastructure engineer focused on network automation and practical, self-hosted LLM deployment, routing, and getting models to do real work rather than benchmarks.
-
gemma4
Context-optimized variant of Google's Gemma 4 12B model, tuned for GPU-constrained inference.
vision tools thinking307 Pulls 1 Tag Updated 3 months ago
-
qwen3.8
Qwen3.8-27B Q4_K_M, default context 131072, tuned for a 32 GB NVIDIA RTX 5090.
vision tools thinking210 Pulls 1 Tag Updated 2 months ago
-
granite4.2
Context-optimized variant of IBM's Granite 4.2 3B model, tuned for lightweight tool-use on GPU-constrained hosts.
137 Pulls 1 Tag Updated 2 months ago
-
granite4.1
Context-optimized variant of IBM's Granite 4.1 3B model, tuned for lightweight tool-use on GPU-constrained hosts.
tools50 Pulls 1 Tag Updated 3 months ago