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 | 30020 | 30020 | 30020 | 30020 |
| 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 | |
|---|---|---|---|---|---|---|---|---|
| WeMM-Embedding-2BOpen weightsTencent · embedding, text | Apache-2.0 | 2.72B | — | 25 Aug 2026 | — | 0 | ✓ fits2.1 GB4bit✓ fits3.6 GB8bit | |
| Whisper Large V3 TurboOpen weightsOpenAI · audio, text | MIT | 808.9M | — | 1 Oct 2024 | — | 0 | ✓ fits1.0 GB4bit✓ fits1.4 GB8bit | |
| WizardLM-2 8x22BOpen weightsMicrosoft · text | —unclassified | — | 65.5K | 16 Apr 2024 | — | 1from $0.62 out | —— | |
| XYZ-Aquila-miniOpen weightsXYZAILab | —unclassified | — | — | — | — | 0 | —— | |
| Yi-34BOpen weights01-ai | —unclassified | — | — | — | — | 0 | —— | |
| Youtu-LLM-2BOpen weightsTencent | Other | 1.96B | — | 31 Dec 2025 | — | 0 | ✓ fits1.6 GB4bit✓ fits2.8 GB8bit | |
| Youtu-LLM-2B-BaseOpen weightsTencent | —unclassified | — | — | — | — | 0 | —— | |
| academic-ds-9BOpen weightsByteDance · text | Apache-2.0 | 9.37B | — | 9 Apr 2025 | — | 0 | ✓ fits5.9 GB4bit✓ fits11.3 GB8bit | |
| alias-gpt2-small-x21Open weightsStanford CRFM · text | Apache-2.0 | — | — | 2 Mar 2022 | — | 0 | —— | |
| amazon/GPT-OSS-20B-P-EAGLEOpen weightsAmazon Web Services | Apache-2.0 | 1.8B | — | 20 Feb 2026 | — | 0 | ✓ fits1.5 GB4bit✓ fits2.6 GB8bit | |
| amazon/MistralLiteOpen weightsAmazon Web Services · text | Apache-2.0 | — | — | 16 Oct 2023 | — | 0 | —— | |
| amazon/Qwen3-Coder-30B-A3B-Instruct-P-EAGLE-long-contextOpen weightsAmazon Web Services | Apache-2.0 | 972.9M3B active | — | 14 May 2026 | — | 0 | ✓ fits1.1 GB4bit✓ fits1.6 GB8bit | |
| amazon/gpt-oss-120b-p-eagleOpen weightsAmazon Web Services | Apache-2.0 | 1.7B | — | 9 Feb 2026 | — | 0 | ✓ fits1.5 GB4bit✓ fits2.5 GB8bit | |
| amazon/gpt-oss-120b-p-eagle-long-contextOpen weightsAmazon Web Services | Apache-2.0 | 1.7B | — | 14 May 2026 | — | 0 | ✓ fits1.5 GB4bit✓ fits2.5 GB8bit | |
| arwen-gpt2-medium-x21Open weightsStanford CRFM · text | —unclassified | — | — | 2 Mar 2022 | — | 0 | —— | |
| aya-101Open weightsCohere | Apache-2.0 | 12.9B | — | 8 Feb 2024 | — | 0 | ✓ fits7.9 GB4bit✓ fits15.4 GB8bit | |
| battlestar-gpt2-small-x49Open weightsStanford CRFM · text | —unclassified | — | — | 2 Mar 2022 | — | 0 | —— | |
| beren-gpt2-medium-x49Open weightsStanford CRFM · text | —unclassified | — | — | 2 Mar 2022 | — | 0 | —— | |
| bert-base-uncasedOpen weightsgoogle-bert | —unclassified | — | — | — | — | 0 | —— | |
| bigvgan_v2_22khz_80band_256xOpen weightsNVIDIA · audio | MIT | — | — | 15 Jul 2024 | — | 0 | —— | |
| bigvgan_v2_44khz_128band_512xOpen weightsNVIDIA · audio | MIT | — | — | 15 Jul 2024 | — | 0 | —— | |
| blip-image-captioning-baseOpen weightsSalesforce · image, text | BSD-3-Clause | — | — | 12 Dec 2022 | — | 0 | —— | |
| blip-image-captioning-largeOpen weightsSalesforce · image, text | BSD-3-Clause | 469.7M | — | 13 Dec 2022 | — | 0 | ✓ fits0.8 GB4bit✓ fits1.0 GB8bit | |
| blip-itm-base-cocoOpen weightsSalesforce | BSD-3-Clause | — | — | 12 Dec 2022 | — | 0 | —— | |
| blip-vqa-baseOpen weightsSalesforce · image, text | BSD-3-Clause | 384.7M | — | 12 Dec 2022 | — | 0 | ✓ fits0.7 GB4bit✓ fits0.9 GB8bit | |
| blip2-flan-t5-xlOpen weightsSalesforce · image, text | MIT | 3.94B | — | 6 Feb 2023 | — | 0 | ✓ fits2.8 GB4bit✓ fits5.0 GB8bit | |
| blip2-opt-2.7bOpen weightsSalesforce · image, text | MIT | 3.74B | — | 6 Feb 2023 | — | 0 | ✓ fits2.6 GB4bit✓ fits4.8 GB8bit | |
| bortOpen weightsAmazon Web Services · text | —unclassified | — | — | 2 Mar 2022 | — | 0 | —— | |
| browsesafeOpen weightsPerplexity AI · text | MIT | 30.5B | — | 14 Nov 2025 | — | 0 | ✓ fits18.1 GB4bit✓ fits35.6 GB8bit | |
| caprica-gpt2-small-x81Open weightsStanford CRFM · text | —unclassified | — | — | 2 Mar 2022 | — | 0 | —— | |
| celebrimbor-gpt2-medium-x81Open weightsStanford CRFM · text | —unclassified | — | — | 2 Mar 2022 | — | 0 | —— | |
| cerebras/DeepSeek-V3.2-REAP-345B-A37BOpen weightsCerebras Systems · text | MIT | 344.9B37B active | — | 9 Dec 2025 | — | 0 | ✗ too large198.8 GB4bit✗ too large397.1 GB8bit | |
| cerebras/DeepSeek-V3.2-REAP-508B-A37BOpen weightsCerebras Systems · text | MIT | 508.4B37B active | — | 9 Dec 2025 | — | 0 | ✗ too large292.8 GB4bit✗ too large585.2 GB8bit | |
| cerebras/GLM-4.5-Air-REAP-82B-A12BOpen weightsCerebras Systems · text | MIT | 81.9B12B active | — | 20 Oct 2025 | — | 0 | ✓ fits47.6 GB4bit✓ fits94.7 GB8bit | |
| cerebras/GLM-4.6-REAP-218B-A32BOpen weightsCerebras Systems · text | MIT | 218.4B32B active | — | 23 Oct 2025 | — | 0 | ✗ too large126.1 GB4bit✗ too large251.6 GB8bit | |
| cerebras/GLM-4.6-REAP-268B-A32BOpen weightsCerebras Systems · text | MIT | 268.8B32B active | — | 24 Oct 2025 | — | 0 | ✗ too large155.1 GB4bit✗ too large309.6 GB8bit | |
| cerebras/GLM-4.7-Flash-REAP-23B-A3BOpen weightsCerebras Systems · text | MIT | 23B3B active | — | 23 Jan 2026 | — | 0 | ✓ fits13.7 GB4bit✓ fits26.9 GB8bit | |
| cerebras/GLM-4.7-REAP-218B-A32BOpen weightsCerebras Systems · text | MIT | 218.4B32B active | — | 10 Jan 2026 | — | 0 | ✗ too large126.1 GB4bit✗ too large251.6 GB8bit | |
| cerebras/GLM-4.7-REAP-268B-A32BOpen weightsCerebras Systems · text | MIT | 268.8B32B active | — | 10 Jan 2026 | — | 0 | ✗ too large155.1 GB4bit✗ too large309.6 GB8bit | |
| cerebras/Kimi-Linear-REAP-35B-A3B-InstructOpen weightsCerebras Systems · text | MIT | 35.1B3B active | — | 6 Nov 2025 | — | 0 | ✓ fits20.7 GB4bit✓ fits40.9 GB8bit | |
| cerebras/MiniMax-M2-REAP-139B-A10BOpen weightsCerebras Systems · text | Other | 139.2B10B active | — | 17 Nov 2025 | — | 0 | ✗ too large80.5 GB4bit✗ too large160.5 GB8bit | |
| cerebras/MiniMax-M2-REAP-162B-A10BOpen weightsCerebras Systems · text | Other | 162B10B active | — | 15 Nov 2025 | — | 0 | ✗ too large93.6 GB4bit✗ too large186.8 GB8bit | |
| cerebras/MiniMax-M2-REAP-172B-A10BOpen weightsCerebras Systems · text | Other | 172.5B10B active | — | 15 Nov 2025 | — | 0 | ✗ too large99.7 GB4bit✗ too large198.9 GB8bit | |
| cerebras/MiniMax-M2.1-REAP-139B-A10BOpen weightsCerebras Systems · text | Other | 139.2B10B active | — | 27 Jan 2026 | — | 0 | ✗ too large80.5 GB4bit✗ too large160.5 GB8bit | |
| cerebras/MiniMax-M2.5-REAP-139B-A10BOpen weightsCerebras Systems · text | Other | 139.2B10B active | — | 18 Feb 2026 | — | 0 | ✗ too large80.5 GB4bit✗ too large160.5 GB8bit | |
| cerebras/MiniMax-M2.5-REAP-172B-A10BOpen weightsCerebras Systems · text | Other | 172.5B10B active | — | 18 Feb 2026 | — | 0 | ✗ too large99.7 GB4bit✗ too large198.9 GB8bit | |
| cerebras/Qwen3-Coder-REAP-25B-A3BOpen weightsCerebras Systems · text | Apache-2.0 | 24.9B3B active | — | 20 Oct 2025 | — | 0 | ✓ fits14.8 GB4bit✓ fits29.1 GB8bit | |
| chatglm2-6bOpen weightsZ.ai (Zhipu AI) | —unclassified | 6B | — | 24 Jun 2023 | — | 0 | ✓ fits4.0 GB4bit✓ fits7.4 GB8bit | |
| chatglm3-6bOpen weightsZ.ai (Zhipu AI) | —unclassified | 6.24B | — | 25 Oct 2023 | — | 0 | ✓ fits4.1 GB4bit✓ fits7.7 GB8bit | |
| chronos-2Open weightsAmazon Web Services · structured | Apache-2.0 | 119.5M | — | 30 Oct 2025 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 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