Aion-3.0 · Ollama

nemotron-3.5-lightning

NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.

tools thinking 30b

135.3K Pulls 11 Tags Updated 2 weeks ago

alicek0914/gemma4-scam

QLoRA fine-tune of Gemma 4 E2B for scam detection. F1 86.1% / FPR 1.1% on a 300-sample real test set. 12-tool function calling for SMS, email, voice transcripts, and OCR'd MMS images.

tools thinking

38 Pulls 1 Tag Updated 3 months ago

odytrice/muse

Meta's Apache 2.0 agentic vision-language model, 30B at 4-bit with 131K context

vision 30b

16 Pulls 2 Tags Updated 1 week ago

ukjin/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill

This model is a distilled version of Qwen/Qwen3-30B-A3B-Instruct designed to inherit the reasoning and behavioral characteristics of its much larger teacher model, deepseek-ai/DeepSeek-V3.1.

tools thinking 4b

2,187 Pulls 2 Tags Updated 11 months ago

milkey/Kalomaze-Qwen3-16B-A3B

Qwen3-16B-A3B is a rendition of Qwen3-30B-A3B by kalomaze.

tools

641 Pulls 3 Tags Updated 1 year ago

LoPld/qwen3-coder-30b-a3b-q4_K_S

Quantized Q4_K_S version of Qwen3-coder 30B FP16 model

tools

116 Pulls 1 Tag Updated 2 weeks ago

njir/njir-now

5 Sovereign AI Models — Edge (1.5B), Reasoning (30B), Professional (22B), Verification (7B), Vision (8B). Unified ecosystem by NJIR.AI.

vision tools thinking 1.5b 7b 8b 22b 30b

4,881 Pulls 15 Tags Updated 3 months ago

huihui_ai/glm-4.7-flash-abliterated

As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

tools thinking

285.8K Pulls 5 Tags Updated 7 months ago

huihui_ai/qwenlong-l1.5-abliterated

QwenLong-L1.5, a long-context reasoning model built upon Qwen3-30B-A3B-Thinking, augmented with memory mechanisms to process tasks far beyond its physical context window.

tools thinking 30b

2,654 Pulls 8 Tags Updated 8 months ago

huihui_ai/tongyi-deepresearch-abliterated

tongyi DeepResearch, an agentic large language model featuring 30 billion total parameters, with only 3 billion activated per token.

tools thinking 30b

3,218 Pulls 5 Tags Updated 11 months ago

dcostenco/prism-coder

Local-first AI tool router. 2B/4B/9B read images (vision); 27B text-only. 14B/32B retired. 99.1-100% routing accuracy (BFCL). 97% of traffic stays local.

vision tools thinking 2b 4b 9b 14b 27b 32b

390 Pulls 6 Tags Updated 1 week ago

anpigon/exaone-3.0-7.8b-instruct-llamafied

110 Pulls 2 Tags Updated 1 year ago

huihui_ai/dolphin3-abliterated

Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.

tools 8b

52.3K Pulls 5 Tags Updated 1 year ago

satgeze/ornith-35b-1m

Ornith-1.0-35B MoE (APEX-Compact 17GB): 1M context, vision, fits 32GB cards. 50/50 needles to 524K.

vision tools thinking

1,117 Pulls 13 Tags Updated 1 month ago

crown/artificium

AGI-0 Labs' Reflection Model : A model created by agi0labs based on mattshumer/Reflection-Llama-3.1-70B, offering similar results in language understanding and generation tasks.

tools

17.1K Pulls 1 Tag Updated 1 year ago

dlasher/Nemotron-3-Super-120B-A12B-UD-IQ4_NL

converted from Unsloth Nemotron-3-Super-120B-A12B-UD-IQ4_NL

tools thinking

2 Pulls 1 Tag Updated 16 hours ago

Tharusha_Dilhara_Jayadeera/singemma

A Sinhala-adapted version of Google’s Gemma 3 4B, continually pre-trained on 10.7M Sinhala sentences with a custom 16k vocabulary using 4-bit LoRA.

219 Pulls 1 Tag Updated 11 months ago

huihui_ai/nemotron-abliterated

Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.

tools 70b

3,104 Pulls 6 Tags Updated 1 year ago

huihui_ai/deepseek-r1-Fusion

DeepSeek-R1-Distill-Qwen-Coder-32B-Fusion-9010 is a mixed model that combines the strengths of two powerful DeepSeek-R1-Distill-Qwen-based models: huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated and huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated.

32b

2,562 Pulls 6 Tags Updated 1 year ago

jace-ai/SmolLM2-German-Instruct

Extensively pre-trained and instruction fine-tuned version of SmolLM2 360M, now supercharged with German language capabilities!

360m

535 Pulls 4 Tags Updated 1 year ago