Meta’s Llama family of open **weights** (subject to Llama license) with reference code, tooling, and downloads via Hugging Face and meta-llama org.
llmopen-weightsmetafoundation-model
Browse & filter
Filter by platform, license text, maturity, maintenance cadence, and editorial tags like privacy-focused or self-hosted. Search matches names, summaries, tags, and use cases.
7 tools match your filters
Mistral’s open-weight checkpoints (e.g. 7B era, Mixtral MoE) and Apache-2.0–licensed **code** alongside proprietary flagship lines—verify each checkpoint.
llmopen-weightsmoeeuropefoundation-model
Top pick
Alibaba’s Qwen family (dense and MoE) with strong multilingual and coding variants; weights and code on Hugging Face under stated licenses per release.
llmopen-weightscodingmultilingualfoundation-model
Top pick
DeepSeek open-weight models (e.g. V3/R1 lineage) with MIT or custom terms per release—high capability coding and reasoning checkpoints.
llmopen-weightsreasoningcodingfoundation-model
Also strong
Google’s smaller open **weights** Gemma line (Gemma 2/3, etc.) with Gemma license terms, plus `gemma.cpp` for lightweight CPU inference.
llmopen-weightsgoogleedgefoundation-model
Honorable mention
Technology Innovation Institute Falcon open weights (7B–180B era) under Apache-2.0 weights for many releases—landmark UAE-led open model line.
llmopen-weightsapache-2foundation-model
Also strong
Google Research pretrained time-series foundation model for forecasting with open Apache-2.0 code and checkpoints.
time-seriesforecastingfoundation-modeltaaft-repositories