Qwen2.5 0.5B fine-tuned on data distilled from GPT 4.1-Nano, 4o, o3, and o4-mini
658 Pulls 1 Tag Updated 1 year ago
minicpm-llama3-2.5-8b-16-v With only 8B parameters, it surpasses widely used proprietary models like GPT-4V-1106, Gemini Pro, Claude 3 and Qwen-VL-Max and greatly outperforms other Llama 3-based MLLMs
567 Pulls 1 Tag Updated 2 years ago
https://habr.com/ru/articles/830332/
1,035 Pulls 1 Tag Updated 2 years ago
Agentic coding model for 24 GB GPUs: TeichAI's Gemma-4-31B Fable-5 agent distill (vision + thinking + tools) with a disciplined coding-agent system prompt baked in. Inspect → reproduce → smallest fix → re-verify.
149 Pulls 1 Tag Updated 1 month ago
Context-optimized variant of IBM's Granite 4.1 3B model, tuned for lightweight tool-use on GPU-constrained hosts.
22 Pulls 1 Tag Updated 4 weeks ago
Generic all purpose model. Occasionally may have notable logic, usually Llama-3_3-Nemotron-Super-49B-v1_5 is preferred.
133 Pulls 1 Tag Updated 9 months ago
129 Pulls 1 Tag Updated 9 months ago
Parable is IBM Granite 4.1 fine-tuned on Claude Fable 5 and GPT-5.5 agent traces. Adds think reasoning to Granite. Sibling: Qwen3 line at parable/qwen3-fable
383 Pulls 10 Tags Updated 1 month ago
Context-optimized variant of Google's Gemma 4 12B model, tuned for GPU-constrained inference.
157 Pulls 1 Tag Updated 4 weeks ago
Gemma 4 Ollama profiles for RTX 4090/5090 across 12B, 26B-A4B, and 31B variants, with multimodal support and native tool calling
476 Pulls 5 Tags Updated 2 months ago
A focused fine-tune of Gemma 4 12B on verifiable Python coding data — every training example’s reasoning leads to code that actually passed its tests.
2,247 Pulls 6 Tags Updated 2 months ago
Gemma 4, fine-tuned to drive ComfyUI. A size ladder of Google's Gemma 4 models QLoRA-trained on 1,055 server-verified tool-use trajectories generated against a live ComfyUI instance — covering the complete comfyui-mcp tool surface
1,100 Pulls 3 Tags Updated 1 month ago
I’m excited to share a new antigenic fine-tune of Gemma-4-12B designed specifically for tool-calling and raw reasoning loops on Apple Silicon.
1,271 Pulls 3 Tags Updated 2 months ago
A fine-tuned version of Gemma 4 12B IT on Vedic wisdom literature blended with general reasoning data.
52 Pulls 2 Tags Updated 2 months ago