146 Pulls 1 Tag Updated 5 days ago
ollama run hf.co/huihui-ai/Huihui-GLM-5.3-Flash-abliterated-GGUF:UD-IQ1_S
43 Pulls 1 Tag Updated 6 days ago
Spark-X2.5-4B abliterated (uncensored) - efficient AI model for chat, writing, coding, reasoning, tools, and agents, 1M-token context, 200+ languages, with refusal behavior removed.
1,854 Pulls 5 Tags Updated 2 weeks ago
Uncensored/Abliterated MiMo-V2.6-Distill-Qwen-9B: coding, agent tasks, visual coding, cybersecurity. Thinking+instruct variants.
1,253 Pulls 9 Tags Updated 1 week ago
Qwen 3.5 Abliterated 9B customized for truthful, direct, and technically rigorous responses. Designed to challenge incorrect assumptions, identify contradictions, avoid hallucinations, and prioritize accuracy over agreement. Strong capabilities in reasoni
1,500 Pulls 1 Tag Updated 2 weeks ago
Verified configuration + measured results for abliterated (uncensored) Qwen3.8-27B running as an autonomous redteam/sysadmin agent, served via llama-swap. This card documents OUR tested configuration and results on live tasks
933 Pulls 1 Tag Updated 2 weeks ago
483 Pulls 1 Tag Updated 1 week ago
Uncensored/Abliterated MiniCPM5-2B with only 10/100 refusals. It achieves 2B-class SOTA, remains competitive with 4B models overall.
686 Pulls 5 Tags Updated 2 weeks ago
468 Pulls 1 Tag Updated 3 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.
1.2M Pulls 36 Tags Updated 3 months ago
Qwen3.8-27B tensor-level abliterated, vision tower and MTP head untouched. 0% over-refusal on XSTest, 0-6% refusal across the A/B suite, no measurable capability loss. Full mmproj vision, tool calling and thinking, 262K context.
211.4K Pulls 20 Tags Updated 1 month ago
Qwen3.6-35b-a3b-abliterated-nvfp4-mtp-mlx
210 Pulls 1 Tag Updated 2 weeks ago
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
401.6K Pulls 17 Tags Updated 5 months 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
278.3K Pulls 1 Tag Updated 4 months ago
Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
77K Pulls 15 Tags Updated 1 month ago
95 Pulls 1 Tag Updated 1 week ago
134 Pulls 1 Tag Updated 4 weeks ago
Qwen3.8-Flash-Next tensor-level abliterated— a latest Qwen4-architecture MoE (~177B total / ~6B active) with vision, reasoning, tool-calling, and 262K context. MLX 4/6/8-bit for Apple Silicon. Research use only.
13.6K Pulls 4 Tags Updated 1 month ago
No Oficial - 26 t/s con 8 VRAM MOE A3B + MPT
22.9K Pulls 1 Tag Updated 2 months ago
50 Pulls 1 Tag Updated 1 week ago