Open models
Every canonical model whose weights can be downloaded, described by measurable properties — licence permissions, parameters, context, release, benchmark ranks, providers, estimated local fit. Openness is a set of observed dimensions here, never a score.
889 downloadable models
Openness explorer
Categories and licence permissions
Left: the downloadable universe by openness category. Right: what the licences on this page allow, counted per category — allowed · restricted · unknown.
- Open source1 0%
- Open weights889 87%
- Restricted weights129 13%
Top licences: Apache License 2.0 (311) · MIT License (125) · Other (unclassified licence) (83) · Creative Commons Attribution-NonCommercial 4.0 (24) · Apple Sample Code / ML Research License (15) · Llama 3.2 Community License (12)
| Category · this page | Commercial use | Redistribution | Derivatives | Hosting |
|---|---|---|---|---|
| Open source n=0 | — | — | — | — |
| Open weights n=50 | 37013 | 37013 | 37013 | 35015 |
| restricted-weights n=0 | — | — | — | — |
Counts read: allowed · restricted · unknown / unclassified — over the 50 models on this page, from each licence's stated terms (ontology).
Downloadable models
889 models · sorted by best benchmark rank
Permissions, in order:commercial use· redistribution· derivatives· hosting allowed restricted unknown
| Model | Licence · permissions | Params | Context | Release | Best results | Providers | Fit 64 GB @4bit · 128 GB @8bit Estimated | |
|---|---|---|---|---|---|---|---|---|
| nemotron-3.5-asr-streaming-0.6bOpen weightsNVIDIA · audio, text | Other | 638M | — | 15 May 2026 | — | 0 | ✓ fits0.9 GB4bit✓ fits1.2 GB8bit | |
| nvidia/llama-nemotron-rerank-1b-v2Open weightsNVIDIA · structured, text | Other | 1.24B | — | 16 Oct 2025 | — | 0 | ✓ fits1.2 GB4bit✓ fits1.9 GB8bit | |
| oOpen weightsw | —unclassified | — | — | — | — | 0 | —— | |
| olmOCR-2-7B-1025Open weightsAllen Institute for AI · image, text | Apache-2.0 | 8.29B | — | 6 Oct 2025 | — | 0 | ✓ fits5.3 GB4bit✓ fits10.0 GB8bit | |
| orpheus-3b-0.1-ftOpen weightsCanopy Labs · audio, text | Apache-2.0 | 3.78B | — | 17 Mar 2025 | — | 0 | ✓ fits2.7 GB4bit✓ fits4.8 GB8bit | |
| orpheus-3b-0.1-pretrainedOpen weightsCanopy Labs · audio, text | Apache-2.0 | 3.78B | — | 4 Mar 2025 | — | 0 | ✓ fits2.7 GB4bit✓ fits4.8 GB8bit | |
| owlv2-base-patch16-ensembleOpen weightsGoogle · image, structured, text | Apache-2.0 | 155M | — | 13 Oct 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.7 GB8bit | |
| parakeet-ctc-1.1bOpen weightsNVIDIA · audio, text | CC-BY-4.0 | 1.06B | — | 28 Dec 2023 | — | 0 | ✓ fits1.1 GB4bit✓ fits1.7 GB8bit | |
| parakeet-tdt-0.6b-v2Open weightsNVIDIA | —unclassified | — | — | — | — | 0 | —— | |
| parakeet-tdt-0.6b-v3Open weightsNVIDIA · audio, text | CC-BY-4.0 | 627.1M | — | 4 Aug 2025 | — | 0 | ✓ fits0.9 GB4bit✓ fits1.2 GB8bit | |
| perplexity-ai/llama-cpp-linux-binariesOpen weightsPerplexity AI | —unclassified | — | — | 17 Jul 2026 | — | 0 | —— | |
| phi-2Open weightsMicrosoft · text | MIT | 2.78B | — | 13 Dec 2023 | — | 0 | ✓ fits2.1 GB4bit✓ fits3.7 GB8bit | |
| pplx-computer-qwen-3-8-27b-dflash2-20260824Open weightsPerplexity AI | Other | 18.8B | — | 25 Aug 2026 | — | 0 | ✓ fits11.3 GB4bit✓ fits22.1 GB8bit | |
| pplx-computer-vllm-dflash2Open weightsPerplexity AI | —unclassified | — | — | 20 Aug 2026 | — | 0 | —— | |
| pplx-embed-context-v1-0.6bOpen weightsPerplexity AI · embedding, text | MIT | 596M | — | 20 Jan 2026 | — | 0 | ✓ fits0.8 GB4bit✓ fits1.2 GB8bit | |
| pplx-embed-context-v1-4bOpen weightsPerplexity AI · embedding, text | MIT | 4.02B | — | 20 Jan 2026 | — | 0 | ✓ fits2.8 GB4bit✓ fits5.1 GB8bit | |
| pplx-embed-v1-0.6bOpen weightsPerplexity AI · embedding, text | MIT | 596M | — | 14 Jan 2026 | — | 0 | ✓ fits0.8 GB4bit✓ fits1.2 GB8bit | |
| pplx-embed-v1-4bOpen weightsPerplexity AI · embedding, text | MIT | 4.02B | — | 20 Jan 2026 | — | 0 | ✓ fits2.8 GB4bit✓ fits5.1 GB8bit | |
| pplx-embed-v1-late-0.6bOpen weightsPerplexity AI · embedding, text | MIT | 595.8M | — | 13 Mar 2026 | — | 0 | ✓ fits0.8 GB4bit✓ fits1.2 GB8bit | |
| pplx-pii-maskingOpen weightsPerplexity AI · structured, text | MIT | 596.1M | — | 16 Jul 2026 | — | 0 | ✓ fits0.8 GB4bit✓ fits1.2 GB8bit | |
| pplx-pii-masking-vllm-tmpOpen weightsPerplexity AI · structured, text | Other | 596.1M | — | 2 Aug 2026 | — | 0 | ✓ fits0.8 GB4bit✓ fits1.2 GB8bit | |
| pplx-qwen-3-8-27b-dflash2-20260819Open weightsPerplexity AI | Other | 18.8B | — | 19 Aug 2026 | — | 0 | ✓ fits11.3 GB4bit✓ fits22.1 GB8bit | |
| privacy-filterOpen weightsOpenAI · structured, text | Apache-2.0 | 1.4B | — | 17 Apr 2026 | — | 0 | ✓ fits1.3 GB4bit✓ fits2.1 GB8bit | |
| pythia-1.4bOpen weightsEleutherAI · text | Apache-2.0 | 1.52B | — | 9 Feb 2023 | — | 0 | ✓ fits1.4 GB4bit✓ fits2.3 GB8bit | |
| pythia-12bOpen weightsEleutherAI · text | Apache-2.0 | 12B | — | 28 Feb 2023 | — | 0 | ✓ fits7.4 GB4bit✓ fits14.3 GB8bit | |
| pythia-14mOpen weightsEleutherAI · text | Apache-2.0 | 14.1M | — | 24 Feb 2026 | — | 0 | ✓ fits0.5 GB4bit✓ fits0.5 GB8bit | |
| pythia-14m-dedupedOpen weightsEleutherAI · text | Apache-2.0 | 39.2M | — | 19 Jul 2023 | — | 0 | ✓ fits0.5 GB4bit✓ fits0.6 GB8bit | |
| pythia-160mOpen weightsEleutherAI · text | Apache-2.0 | 212.7M | — | 8 Feb 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.7 GB8bit | |
| pythia-160m-dedupedOpen weightsEleutherAI · text | Apache-2.0 | 212.7M | — | 8 Feb 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.7 GB8bit | |
| pythia-160m-seed1Open weightsEleutherAI · text | Apache-2.0 | 212.7M | — | 15 Feb 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.7 GB8bit | |
| pythia-160m-seed2Open weightsEleutherAI · text | Apache-2.0 | 212.7M | — | 15 Feb 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.7 GB8bit | |
| pythia-160m-seed3Open weightsEleutherAI | Apache-2.0 | 212.7M | — | 15 Feb 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.7 GB8bit | |
| pythia-1bOpen weightsEleutherAI · text | Apache-2.0 | 1.08B | — | 10 Mar 2023 | — | 0 | ✓ fits1.1 GB4bit✓ fits1.7 GB8bit | |
| pythia-2.8bOpen weightsEleutherAI · text | Apache-2.0 | 2.91B | — | 13 Feb 2023 | — | 0 | ✓ fits2.2 GB4bit✓ fits3.9 GB8bit | |
| pythia-410mOpen weightsEleutherAI · text | Apache-2.0 | 506M | — | 13 Feb 2023 | — | 0 | ✓ fits0.8 GB4bit✓ fits1.1 GB8bit | |
| pythia-410m-dedupedOpen weightsEleutherAI · text | Apache-2.0 | 506M | — | 13 Feb 2023 | — | 0 | ✓ fits0.8 GB4bit✓ fits1.1 GB8bit | |
| pythia-6.9bOpen weightsEleutherAI · text | Apache-2.0 | 6.99B | — | 14 Feb 2023 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.5 GB8bit | |
| pythia-70mOpen weightsEleutherAI | Apache-2.0 | 95.6M | — | 13 Feb 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 GB8bit | |
| pythia-70m-dedupedOpen weightsEleutherAI · text | Apache-2.0 | 95.6M | — | 13 Feb 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 GB8bit | |
| resnet-50Open weightsMicrosoft · image, structured | Apache-2.0 | 25.6M | — | 16 Mar 2022 | — | 0 | ✓ fits0.5 GB4bit✓ fits0.5 GB8bit | |
| scibert_scivocab_uncasedOpen weightsAllen Institute for AI | —unclassified | — | — | 2 Mar 2022 | — | 0 | —— | |
| sd-turboOpen weightsStability AI · image, text | —unclassified | 865.9M | — | 27 Nov 2023 | — | 0 | ✓ fits1.0 GB4bit✓ fits1.5 GB8bit | |
| sd-vae-ft-emaOpen weightsStability AI | MIT | 83.7M | — | 13 Oct 2022 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 GB8bit | |
| sd-vae-ft-mseOpen weightsStability AI | MIT | 83.7M | — | 13 Oct 2022 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 GB8bit | |
| sdxl-turboOpen weightsStability AI · image, text | Other | 2.57B | — | 27 Nov 2023 | — | 0 | ✓ fits2.0 GB4bit✓ fits3.5 GB8bit | |
| sdxl-vaeOpen weightsStability AI | MIT | 83.7M | — | 21 Jun 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 GB8bit | |
| siglip-base-patch16-224Open weightsGoogle · image, structured, text | Apache-2.0 | 203.2M | — | 30 Sept 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.7 GB8bit | |
| siglip-base-patch16-512Open weightsGoogle | —unclassified | — | — | — | — | 0 | —— | |
| siglip-so400m-patch14-384Open weightsGoogle · image, structured, text | Apache-2.0 | 878M | — | 8 Jan 2024 | — | 0 | ✓ fits1.0 GB4bit✓ fits1.5 GB8bit | |
| siglip2-base-patch16-224Open weightsGoogle · image, structured, text | Apache-2.0 | 375.2M | — | 17 Feb 2025 | — | 0 | ✓ fits0.7 GB4bit✓ fits0.9 GB8bit |
Best results = rank inside each benchmark's primary comparability group; several dimensions are shown side by side and never combined. Fit columns are estimates (64 GB device at 4-bit, 128 GB at 8-bit, 8K context) — method on /methodology. unclassified = the raw licence label is not yet mapped in the ontology.
MethodUniverse = canonical models whose weights can be downloaded (open-weights, open-source, restricted-weights). hardware_fit values are ESTIMATES (see /methodology); best_results are ranks inside each benchmark's primary comparability group — no composite score. /methodology