262 Pulls 1 Tag Updated 5 days ago
No Oficial - 26 t/s con 8 VRAM MOE A3B + MPT
10.6K Pulls 1 Tag Updated 3 weeks ago
522 Pulls 11 Tags Updated 2 weeks ago
456 Pulls 8 Tags Updated 2 weeks ago
291 Pulls 1 Tag Updated 2 weeks ago
Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
853.3K Pulls 36 Tags Updated 1 month ago
Qwythos-V2-Abliterated-GGUF + Patched to natively support VSC extension by patching the jinja template issue
305 Pulls 3 Tags Updated 2 weeks ago
231 Pulls 14 Tags Updated 2 weeks ago
Cipher-Abliterated is an adaptive conversational AI system designed for flexible interaction, enhanced creative reasoning, and less restrictive conversational behavior while maintaining structured output and technical usability. It is optimized for users
278K Pulls 1 Tag Updated 2 months ago
134 Pulls 1 Tag Updated 1 week ago
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
492.2K Pulls 58 Tags Updated 4 months ago
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
299.2K Pulls 17 Tags Updated 3 months ago
158 Pulls 1 Tag Updated 1 week ago
205 Pulls 1 Tag Updated 3 weeks ago
94 Pulls 14 Tags Updated 2 weeks ago
97K Pulls 1 Tag Updated 5 months ago
99 Pulls 1 Tag Updated 4 weeks ago
Abliterated build of Qwythos-9B-Claude-Mythos, a Claude-style creative & reasoning model (Qwen3.5-9B base) with refusals further reduced via the Heretic library.
12.4K Pulls 6 Tags Updated 1 month ago
Fully decensored Gemma 4 12B (abliterated with Heretic) — 0/100 genuine refusals at KL 0.0284, i.e. near-zero capability loss.
15.1K Pulls 3 Tags Updated 2 months ago
Quantized GGUF of hf.co/OpenYourMind/gemma-4-12B-it-abliterated-uncensored
13.3K Pulls 3 Tags Updated 2 months ago