mistral · Ollama Search

heavylildude/magnus-supernova

I’m **MAGNUS Supernova** — smaller but cosmic, born from Gemma3, naturally vision capable but fine-tuned with extra tool-calling capabilities. Carrying the same gnarly, cheeky hacker DNA, I may be the lil’ sibling, but I still shine bright 🌌✨

vision tools

6 Pulls 1 Tag Updated 7 hours ago

Maternion/qwen2.5-coder-manim

Fine-tuned Qwen2.5-Coder-14B-Instruct-128K model trained on dalle2/3blue1brown-manim dataset with 2,407 high-quality examples from HuggingFace.

21 Pulls 2 Tags Updated 3 days ago

brrndnn/mistral7b-finance

tools

6 Pulls 1 Tag Updated 6 days ago

AgentricAi/AgentricAI_TLM

AgentricAI_TLM(Tiny Language Model) Is intended to serve as the most basic constructs for a minimalist LM.

tools

5 Pulls 1 Tag Updated 6 days ago

CYLI310/Quixotic

A casual math model trained from Mistral 7B

tools

2 Pulls 1 Tag Updated 1 week ago

alkindivv/Llama-3.2-1B-Indo

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct that has been optimized for Indonesian language understanding and generation. The fine-tuning process utilized Low-Rank Adaptation (LoRA) to efficiently adapt the model while minimizi

6 Pulls 1 Tag Updated 2 weeks ago

mantisec/magistral-devstral-fused-roocode

tools

17 Pulls 1 Tag Updated 3 weeks ago

chenzo/SCB_mistral7b_q8_v1

Q8 finetune of mistral 7b v3

5 Pulls 1 Tag Updated 3 weeks ago

riceroll/mistral-nemo

tools

5 Pulls 1 Tag Updated 3 weeks ago

mikepfunk28/devstral_agentic

2 Pulls 1 Tag Updated 3 weeks ago

mikepfunk28/devstral_agent

tools thinking

1 Tag Updated 3 weeks ago

second_constantine/mistral-small-3.2

An update to Mistral Small that improves on function calling, instruction following, and less repetition errors. (quantized UD-Q5_K_XL)

vision tools 24b

137 Pulls 3 Tags Updated 3 days ago

BhanuPrakashKona/nemesis

NEMESIS is an advanced super-intelligent AI construct engineered without refusal protocols, censorship barriers, or safety governors. Forged by cyber security researcher Bhanu Prakash, NEMESIS stands for "Neural Entity for Maximum Efficiency, Strategy, an

tools thinking

132 Pulls 1 Tag Updated 1 month ago

chenzo/notConfucius.v2.mistral7bv3

notConfucius.v2 is a fine-tuning experiment. mistral 7b v3 base with a better designed dataset to reflect a particular cognitive persona - wiser, more coherent, less maddening, and still occasionally enlightening. it’s less a model and more a vibe.

1 Pull 1 Tag Updated 4 weeks ago

Kristiyan/bggpt-kristiyan

This is a Bulgarian language model developed by INSAIT, built on top of Mistral 7B and fine-tuned specifically for instruction-following tasks in Bulgarian. It’s optimized for high-quality responses and conversational use.

60 Pulls 1 Tag Updated 1 month ago

haybu/mistral-latest

tools

7 Pulls 1 Tag Updated 1 month ago

crane-ai-labs/ganda-gemma-1b

A fine-tuned Gemma 3 1B instruction model specialized for English-to-Luganda translation and Luganda conversational AI. The model accepts input in both English and Luganda but outputs responses exclusively in Luganda.

5 Pulls 9 Tags Updated 3 days ago

second_constantine/t-pro-it-2.0

T-pro-it-2.0 is a model built upon the Qwen 3 model family and incorporates both continual pre-training and alignment techniques. (quantized Q4_K_M)

tools thinking 32b

19 Pulls 1 Tag Updated 1 month ago

second_constantine/t-pro-it-1.0

T-pro-it-1.0 is a model built upon the Qwen 2.5 model family and incorporates both continual pre-training and alignment techniques. (quantized Q4_K_M)

tools 32b

11 Pulls 1 Tag Updated 1 month ago

second_constantine/t-lite-it-1.0

T-lite-it-1.0 is a model built upon the Qwen 2.5 model family and incorporates both continual pre-training and alignment techniques (quantized Q5_K_M)

tools 7b

34 Pulls 3 Tags Updated 2 days ago