DEV Community

30 Days of Open-Weight AI Series' Articles

Back to AI Explore's Series
Qwen3.8-27B: The Open-Weight LLM That Fits One Serious GPU — Day 1/30
Cover image for Qwen3.8-27B: The Open-Weight LLM That Fits One Serious GPU — Day 1/30

Qwen3.8-27B: The Open-Weight LLM That Fits One Serious GPU — Day 1/30

1
Comments
6 min read
Ollama: The One-Command Front Door to Local, Open-Weight LLM Inference — Day 2/30
Cover image for Ollama: The One-Command Front Door to Local, Open-Weight LLM Inference — Day 2/30

Ollama: The One-Command Front Door to Local, Open-Weight LLM Inference — Day 2/30

1
Comments
6 min read
Mistral Small 3.2 24B: The Open-Weight AI Model That Fits One Workstation GPU — Day 3/30
Cover image for Mistral Small 3.2 24B: The Open-Weight AI Model That Fits One Workstation GPU — Day 3/30

Mistral Small 3.2 24B: The Open-Weight AI Model That Fits One Workstation GPU — Day 3/30

1
Comments
6 min read
Unsloth: The Fine-Tuning Tool That Lets You Own an Open-Weight LLM — Day 4/30
Cover image for Unsloth: The Fine-Tuning Tool That Lets You Own an Open-Weight LLM — Day 4/30

Unsloth: The Fine-Tuning Tool That Lets You Own an Open-Weight LLM — Day 4/30

1
Comments 1
5 min read
gpt-oss-120b: OpenAI's Open-Weight AI Model for Cheap High-Volume Inference — Day 5/30
Cover image for gpt-oss-120b: OpenAI's Open-Weight AI Model for Cheap High-Volume Inference — Day 5/30

gpt-oss-120b: OpenAI's Open-Weight AI Model for Cheap High-Volume Inference — Day 5/30

Comments
6 min read
Open-Weight AI in Your Pocket: The Local LLMs Already Running on Phones — Day 6/30
Cover image for Open-Weight AI in Your Pocket: The Local LLMs Already Running on Phones — Day 6/30

Open-Weight AI in Your Pocket: The Local LLMs Already Running on Phones — Day 6/30

1
Comments
6 min read
DeepSeek-V4-Flash: The Open-Weight AI Model Pricing Inference at $0.08/M — Day 7/30
Cover image for DeepSeek-V4-Flash: The Open-Weight AI Model Pricing Inference at $0.08/M — Day 7/30

DeepSeek-V4-Flash: The Open-Weight AI Model Pricing Inference at $0.08/M — Day 7/30

1
Comments
6 min read
Gemma 4 26B A4B: The Open-Weight AI Model That Wakes Only 4B Params — Day 8/30
Cover image for Gemma 4 26B A4B: The Open-Weight AI Model That Wakes Only 4B Params — Day 8/30

Gemma 4 26B A4B: The Open-Weight AI Model That Wakes Only 4B Params — Day 8/30

1
Comments
4 min read
llama.cpp: The Open-Weight AI Inference Engine Behind Local LLMs — Day 9/30
Cover image for llama.cpp: The Open-Weight AI Inference Engine Behind Local LLMs — Day 9/30

llama.cpp: The Open-Weight AI Inference Engine Behind Local LLMs — Day 9/30

Comments
6 min read
NVIDIA Nemotron 3 Nano 30B: The Open-Weight AI Model Given Away Free — Day 10/30
Cover image for NVIDIA Nemotron 3 Nano 30B: The Open-Weight AI Model Given Away Free — Day 10/30

NVIDIA Nemotron 3 Nano 30B: The Open-Weight AI Model Given Away Free — Day 10/30

Comments
6 min read
vLLM: The Open-Weight AI Inference Server Built for Production LLM Serving — Day 11/30
Cover image for vLLM: The Open-Weight AI Inference Server Built for Production LLM Serving — Day 11/30

vLLM: The Open-Weight AI Inference Server Built for Production LLM Serving — Day 11/30

Comments
6 min read
SGLang: The Open-Weight AI Inference Engine Built for Prefix Reuse — Day 12/30
Cover image for SGLang: The Open-Weight AI Inference Engine Built for Prefix Reuse — Day 12/30

SGLang: The Open-Weight AI Inference Engine Built for Prefix Reuse — Day 12/30

1
Comments
6 min read
Inference Economics: The Self-Hosted vs API Framework for Open-Weight LLMs — Day 13/30
Cover image for Inference Economics: The Self-Hosted vs API Framework for Open-Weight LLMs — Day 13/30

Inference Economics: The Self-Hosted vs API Framework for Open-Weight LLMs — Day 13/30

1
Comments
6 min read
IBM Granite 4.1 8B: The Open-Weight LLM Built for Enterprise RAG — Day 14/30
Cover image for IBM Granite 4.1 8B: The Open-Weight LLM Built for Enterprise RAG — Day 14/30

IBM Granite 4.1 8B: The Open-Weight LLM Built for Enterprise RAG — Day 14/30

Comments
6 min read
Open-Weight AI on the Factory Floor: Why Air-Gapped Manufacturing Runs Local LLMs — Day 15/30
Cover image for Open-Weight AI on the Factory Floor: Why Air-Gapped Manufacturing Runs Local LLMs — Day 15/30

Open-Weight AI on the Factory Floor: Why Air-Gapped Manufacturing Runs Local LLMs — Day 15/30

1
Comments
6 min read
Qwen3-VL 8B: The Open-Weight Vision-Language Model Reading Your Receipts — Day 16/30
Cover image for Qwen3-VL 8B: The Open-Weight Vision-Language Model Reading Your Receipts — Day 16/30

Qwen3-VL 8B: The Open-Weight Vision-Language Model Reading Your Receipts — Day 16/30

Comments
6 min read
Open-Weight AI in Drone Tech: How YOLO Flies on a Jetson Nano — Day 17/30
Cover image for Open-Weight AI in Drone Tech: How YOLO Flies on a Jetson Nano — Day 17/30

Open-Weight AI in Drone Tech: How YOLO Flies on a Jetson Nano — Day 17/30

Comments
5 min read
Open-Weight AI in Space: Gemma 3 Runs Onboard NASA's YAM-9 Satellite — Day 18/30
Cover image for Open-Weight AI in Space: Gemma 3 Runs Onboard NASA's YAM-9 Satellite — Day 18/30

Open-Weight AI in Space: Gemma 3 Runs Onboard NASA's YAM-9 Satellite — Day 18/30

Comments
6 min read
Xiaomi MiMo-V2.5: Open-Weight Omnimodal AI for Self-Hosted Voice and Video — Day 19/30
Cover image for Xiaomi MiMo-V2.5: Open-Weight Omnimodal AI for Self-Hosted Voice and Video — Day 19/30

Xiaomi MiMo-V2.5: Open-Weight Omnimodal AI for Self-Hosted Voice and Video — Day 19/30

1
Comments 1
6 min read