Open Source LLMs

Open Source LLMs tools for large language models.

Available Tools

Mistral (Large 3, Ministral, Small)

• Website: https://mistral.ai/

• Description: Open-source models: 675B MoE Large, small multimodal Ministral, Apache 2.0 (2025).

• Pricing: 🆓

DeepSeek (V3.2, R1)

• Website: https://deepseek.com/

• Description: Open-source reasoning models matching GPT-5, MoE architecture (671B).

• Pricing: 🆓

LLaMA 4 (Scout, Maverick)

• Website: https://ai.meta.com/llama/

• Description: Meta's MoE models: 109B Scout (10M ctx), 400B Maverick multimodal.

• Pricing: 🆓

Qwen 3 (VL-235B)

• Website: https://qwenlm.github.io/

• Description: Alibaba's trillion-parameter hybrid with vision-language support.

• Pricing: 🆓

GLM-4.5

• Website: https://github.com/THUDM/GLM-4

• Description: Zhipu's 130B model, #2 on LMArena with MIT license.

• Pricing: 🆓

Kimi K2

• Website: https://moonshot.cn/

• Description: Moonshot AI's robust Chinese LLM with open research.

• Pricing: 🆓

Gemma 3

• Website: https://ai.google.dev/gemma

• Description: Google's lightweight open model with Gemma license.

• Pricing: 🆓

Falcon 3

• Website: https://falconllm.tii.ae/

• Description: Latest open-source LLM by TII with improved performance.

• Pricing: 🆓