With the plug and playness of Ollama models on limited systems; why should some models be left out of reach? or why should some models not be here due to porting quirks when the base models are already here? Time to pickup the pieces and hack it!
-
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Qwen3.6-35B-A3B uncensored by HauhauCS. 0/465 Refusals. Patched to have vision support; Fully functional, 100% of what the original authors intended - just without the refusals. These are meant to be the best lossless uncensored models out there.
vision tools thinking19K Pulls 5 Tags Updated 3 weeks ago
-
Gemma-4-Uncensored-HauhauCS-Aggressive
Bringing the monolithic GGUF to HauhauCS's work of aggressively uncensoring Gemma 4. For edge models having full audio and vision support; there are multi-modal specific focused models available [Vision OR Sound].
vision tools thinking audio e2b e4b12.7K Pulls 8 Tags Updated 1 month ago
-
Qwen3.5-Uncensored-HauhauCS-Aggressive
Monolith GGUF of HauhauCS' Qwen3.5-Uncensored-Aggressive model family. With full vision support, patched model.
vision tools thinking 4b 9b8,543 Pulls 3 Tags Updated 1 month ago
-
Qwopus3.5
Qwopus3.5-v3 is a reasoning-enhanced model family fine-tune of Qwen3.5 designed to improve reasoning stability and correctness, optimize inference efficiency, and enhance cross-task generalization capabilities, especially in programming.
vision tools thinking 4b 9b 27b7,876 Pulls 7 Tags Updated 1 month ago
-
qwen3.5-opus
Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled-v2; https://huggingface.co/Jackrong/; has vision properly merged and efficiently quantified.
vision tools thinking 4b 9b 27b4,798 Pulls 4 Tags Updated 1 month ago
-
Qwen3.6-27B-Uncensored-HauhauCS-Balancedvision tools thinking
1,850 Pulls 1 Tag Updated 2 weeks ago
-
Qwen3.6-35B-A3B-APEX
APEX (Adaptive Precision for EXpert Models) quantizations of Qwen/Qwen3.6-35B-A3B, to try to optimize performance.
vision tools thinking1,202 Pulls 2 Tags Updated 3 weeks ago
-
chandra-ocr-2
Chandra-OCR-2 from Datalab is a state-of-the-art OCR model that outputs structured markdown, HTML, or JSON while preserving precise layout information from images and PDFs across 90+ languages. there is another of this in Ollama but unpatched [no vision?]
vision tools thinking1,049 Pulls 2 Tags Updated 1 month ago
-
unsloth-deepseek-r1
unslothed-deepseek-r1, converted to ollama from the repo: https://huggingface.co/unsloth
8b 14b690 Pulls 2 Tags Updated 1 year ago
-
Qwen3.5-APEX
Qwen3.5-35B-A3B APEX GGUF -- A Novel MoE-Aware Mixed-Precision Quantization Technique Brought to you by the LocalAI team -- the creators of LocalAI the open-source AI engine that runs any model - LLMs, vision, image - on any hardware.
vision tools thinking542 Pulls 2 Tags Updated 1 month ago
-
gemma-4-26B-A4B-it-Claude-Opus-Distill-APEX-GGUFvision tools thinking
541 Pulls 1 Tag Updated 3 weeks ago
-
Gemopus-4-it
Monolith Patched Ollama gguf of Jackrong's work to make Gemma4 e4b seem more helpful and reduce the "Wikipedia Tone". [With multimodal focused models: audio or vision support]
vision tools thinking audio e4b497 Pulls 5 Tags Updated 1 month ago
-
Qwopus3.6
As part of the Qwopus series, Qwopus3.6 continues the same core direction established in earlier versions: stronger reasoning quality, a more stable answer structure, and less stylistic drift across long-form responses.
vision tools thinking 27b396 Pulls 3 Tags Updated 2 weeks ago
-
mistral3-unsloth
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B. This model is unsloth version of the model.
tools208 Pulls 1 Tag Updated 1 year ago
-
Jan-code
Built on top of Jan-v3-4B-base-instruct; Jan-code is designed to be a practical coding model you can run locally and iterate on quickly—useful for everyday code tasks and as a lightweight “worker” model in agentic workflows.
tools158 Pulls 4 Tags Updated 1 month ago
-
Jan-v2-VL
Jan-v2-VL is a family of 8B-parameter vision–language models for long-horizon, multi-step tasks in real software environments (e.g., browsers and desktop apps).
vision tools thinking88 Pulls 10 Tags Updated 2 months ago
-
Jan-v3
Jan-v3 is a compact 4B-parameter model that leverages distillation from a larger teacher to maintain strong general performance and broad applicability while avoiding typical capacity limitations.
tools78 Pulls 4 Tags Updated 2 months ago
-
Jan-v3.5-4B
Jan-v3.5-4B is a fine-tuned variant of Jan-v3-4B-base-instruct, specialized on math reasoning and identity datasets. It retains the general-purpose capabilities of the base model while delivering improved mathematical problem-solving.
tools39 Pulls 2 Tags Updated 1 month ago
-
Mistral-Small-3.1
unsloth
tools35 Pulls 1 Tag Updated 1 year ago
-
Qwen3.6-27B-Uncensored-HauhauCS-Aggressive
Qwen3.6-27B uncensored by HauhauCS. 0/465 Refusals. Patched to have vision support; Fully functional, 100% of what the original authors intended - just without the refusals. These are meant to be the best lossless uncensored models out there.