Open-source Models

Hugging Face repo for DBRX Instruct checkpoints under an open license for local inference and finetuning.

MosaicML’s Apache-licensed 7B family (base/instruct/long-context) widely used as a fine-tuning base.

Open Efficient Language Models (270M–3B) with code, weights, and training recipes for reproducible local use.

Attention-free RNN-style open models with transformer-level performance and constant-memory inference.

Compact 1.1B Llama-compatible model; popular GGUF quantizations make it fast on CPUs/GPUs locally.

Ultra-small open models (135M/360M/1.7B) tailored for on-device and constrained local deployments.

TII’s newer open series (text+VLM variants) optimized for efficient inference; Apache-style release.

Edge-friendly multimodal 8B model (images/video) with quantized variants for low-VRAM local inference.

Open multimodal family (1B–78B); 78B surpasses 70% on MMMU; broad image/video understanding.

Fully open multimodal (images/video+text) models & training stack; strong results and reproducible recipes.

01.AI’s upgraded Yi family (6B/34B) with improved instruction following and coding; widely used in local stacks.

Open-weight 32B RL-trained reasoning model reported to rival larger systems while remaining locally runnable.

Microsoft’s 14B open-weight reasoning model yielding strong complex-task performance with modest hardware.

Fully open training data, code, and checkpoints; transparent 7B/13B/32B family for reproducible research and apps.

Apache-licensed 2B–8B family with long context options; optimized for enterprise/local deployments.