44 Pulls 1 Tag Updated 2 weeks ago
Custom model for coding with agents to use locally with 16gb or 2x8gb GPUs (working fine...)
988 Pulls 1 Tag Updated 2 months ago
Quantized GGUF of hf.co/DuoNeural/Gemma4-12B-IT-Abliterated
468 Pulls 3 Tags Updated 2 months ago
High-tier 12B Gemma 4 model with Unsloth Dynamic QAT & MTP. Packs deep multimodal reasoning, an aggressive 4-token speculative draft window, and a massive 128K context capacity. Tailored for heavy codebase ingestion and reasoning tasks.
547 Pulls 1 Tag Updated 2 weeks ago
Context-optimized variant of Google's Gemma 4 12B model, tuned for GPU-constrained inference.
61 Pulls 1 Tag Updated 1 week ago
Quantized GGUF of hf.co/OpenYourMind/gemma-4-12B-it-abliterated-uncensored
13.3K Pulls 3 Tags Updated 2 months ago
Gemma 4 12B uncensored, 1.5M max context: certified 10/10 to 1.31M on a 32GB card. Vision included.
3,266 Pulls 1 Tag Updated 1 month ago
Gemma 4 12B uncensored: first Gemma certified 10/10 at 1M, fits a 32GB card. Vision included.
1,022 Pulls 1 Tag Updated 1 month ago
Gemma 4 12B (QAT Q4_0) with Multi-Token Prediction speculative decoding — a fast, tool-capable local model for 16 GB - Apple Silicon Macs (~21 tok/s, ~1.4× via MTP).
727 Pulls 1 Tag Updated 1 month ago
Gemma 4 12B agent-tuned for Hermes Agent and other local agent harnesses. One built for 20GB GPUs the other for 8GB GPUs.
543 Pulls 2 Tags Updated 1 month ago
Gemma 4 Ollama profiles for RTX 4090/5090 across 12B, 26B-A4B, and 31B variants, with multimodal support and native tool calling
428 Pulls 5 Tags Updated 2 months ago
A fine-tuned version of Gemma 4 12B IT on Vedic wisdom literature blended with general reasoning data.
48 Pulls 2 Tags Updated 1 month ago
😈 Uncensored Gemma 4 12B (QAT Q4) for Ollama. 👁️ Audio,🎙️, 🛠️Tool Calling, MTP, Rust, Linux, Windows AI Coding Agents & Multimodal Local AI. 🚀
1,489 Pulls 1 Tag Updated 3 weeks ago
Fully decensored Gemma 4 12B (abliterated with Heretic) — 0/100 genuine refusals at KL 0.0284, i.e. near-zero capability loss.
15.5K Pulls 3 Tags Updated 2 months ago
Decensored (abliterated) Gemma 4 12B — refusals removed with Heretic while keeping the base model's intelligence (KL 0.0154, 0 true refusals). For uncensored assistant and 18+ companion/roleplay use.
7,604 Pulls 4 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.
2,052 Pulls 6 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.
1,107 Pulls 3 Tags Updated 2 months ago
a Gemma-4 12B coding model with refusals dramatically reduced via the Heretic library.
872 Pulls 6 Tags Updated 1 month ago
THOX.ai tool-calling agent. Gemma-4-12B-it QLoRA fine-tune, Q4_K_M, with tools and thinking.
12 Pulls 1 Tag Updated 2 weeks ago
THOX.ai flagship local assistant. Gemma-4-12B QLoRA fine-tune, Q4_K_M. Pairs with ThoxNova-12B-Agent for tool use.
9 Pulls 1 Tag Updated 2 weeks ago