Models

MiMo-V2.6-Distill-Qwen-9B is Xiaomi MiMo’s 9B model for code and agent workflows

100% Uncensored (0.0% Refusal) — Qwen 3.8 Uncensored Multimodal Suite: 9B (Qwen3.8-2.4T-A95B Full-Parameter Distill + Heretic Uncensored) & 27B Flagship (256K Context, Vision, Tools & Thinking) for SecOps & Systems Engineering.

RANA: an abliterated, uncensored Qwen3.5-9B with vision, thinking and tools, from Abliterant.

Community redistribution of a Qwen3.5-9B Heretic merge build — not THOX-trained. Vision probe passed 2026-10-31; full evaluation pending. Apache-2.0.

Four-way omnimerge_v2 merge over Qwen3.5-9B (DeltaCoder 0.55 / Qwopus3.5-9B-Coder 0.30 / Ornith-1.5-9B 0.15), tuned for multi-turn agentic coding — it finishes tasks instead of looping. 9B dense, DFlash drafter

Unsloth Dynamic Q4_K_XL with MTP & Vision

Community redistribution of a Qwen3.5-9B Mythos Heretic build — not THOX-trained. Full evaluation pending. Apache-2.0.

The foundational weights of Qwen/Qwen3.5-9B with selected specialization to maximize coding + agentic work at a small size using distillation/donar weights. ~7 GB loaded. Q4_K_M.

HuatuoGPT-3-9B is a medical LLM built on Qwen3.5-9B with One-stage Policy Optimization (OnePO). OnePO adapts language models to medicine in a single reinforcement-learning stage, without preceding domain-specific supervised fine-tuning. Q4_K_M Version.

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.

Text + Vision Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-MTP-GGUF-NVFP4

Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Qwen3.8-9B-Distill is a dense 9B reasoning model: it brings the reasoning behaviour of a frontier-scale teacher (Qwen3.8, 2.4T-A95B) into a model that fits on a single consumer GPU. Every answer opens with a <think> block learned from real teacher traces,

MiMo-V2.6-Distill-9B (Qwen3.5-9B SFT): coding, agent tasks, visual coding, cybersecurity. Thinking + instruct quants, multimodal.

Uncensored/Abliterated MiMo-V2.6-Distill-Qwen-9B: coding, agent tasks, visual coding, cybersecurity. Thinking+instruct variants.

Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash - is an efficient reasoning model distilled using high-quality data from DeepSeek-V4. + vision. ollama v.0.30.0-rc20 +

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

Huihui Qwen3.5 9B abliterated, GGUF Q4_K_M. A standalone release packaged by Interim Labs.

Custom model for coding with agents to use locally with 16gb GPUs (working very fine...)