Custom model for coding with agents to use locally with 16gb or 2x8gb GPUs (working fine...)
Quantized GGUF of hf.co/DuoNeural/Gemma4-12B-IT-Abliterated
Quantized GGUF of hf.co/OpenYourMind/gemma-4-12B-it-abliterated-uncensored
Gemma 4 12B uncensored, 1.5M max context: certified 10/10 to 1.31M on a 32GB card. Vision included.
Gemma 4 12B uncensored: first Gemma certified 10/10 at 1M, fits a 32GB card. Vision included.
Gemma 4 12B agent-tuned for Hermes Agent and other local agent harnesses. One built for 20GB GPUs the other for 8GB GPUs.
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.
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).
Gemma 4 Ollama profiles for RTX 4090/5090 across 12B, 26B-A4B, and 31B variants, with multimodal support and native tool calling
Context-optimized variant of Google's Gemma 4 12B model, tuned for GPU-constrained inference.
A fine-tuned version of Gemma 4 12B IT on Vedic wisdom literature blended with general reasoning data.
Gargantua Pro Gen 1: our largest model, Gemma 4 12B fine-tuned for openTARS tools, with vision. For computers with room for 8 GB or more.
Text-only Gemma 4 12B GGUF files. Default: q4_0. TurinTech models, built with Artemis. Measured Q4_0: Mean KLD 0.156, Same top p 86.8% vs BF16 on WikiText-2 test; protocol a100-2026-10-24.
Fully decensored Gemma 4 12B (abliterated with Heretic) — 0/100 genuine refusals at KL 0.0284, i.e. near-zero capability loss.
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.
a Gemma-4 12B coding model with refusals dramatically reduced via the Heretic library.
😈 Uncensored Gemma 4 12B (QAT Q4) for Ollama. 🎙️ Audio, 🛠️ Tool Calling, MTP, MCP, Rust 1.99.1 , Linux, Windows AI Coding Agents & Multimodal Local AI. 🚀
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.