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.
950 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 weights869 91%
- Restricted weights80 8%
Top licences: Apache License 2.0 (275) · Other (unclassified licence) (115) · MIT License (92) · Creative Commons Attribution-NonCommercial 4.0 (22) · 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=43 | 25018 | 25018 | 25018 | 25018 |
| restricted-weights n=7 | 070 | 700 | 700 | 070 |
Counts read: allowed · restricted · unknown / unclassified — over the 50 models on this page, from each licence's stated terms (ontology).
Downloadable models
950 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 | |
|---|---|---|---|---|---|---|---|---|
| granite-4.0-1b-baseOpen weightsIBM | —unclassified | — | — | — | — | 0 | —— | |
| granite-docling-258MOpen weightsIBM | Apache-2.0 | 257.5M | — | 19 May 2025 | — | 0 | ✓ fits0.7 GB4bit✓ fits0.8 GB8bit | |
| granite-embedding-125m-englishOpen weightsIBM | Apache-2.0 | 124.7M | — | 4 Dec 2024 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 GB8bit | |
| granite-embedding-311m-multilingual-r2Open weightsIBM | Apache-2.0 | 311.7M | — | 20 Apr 2026 | — | 0 | ✓ fits0.7 GB4bit✓ fits0.9 GB8bit | |
| granite-embedding-97m-multilingual-r2Open weightsIBM | Apache-2.0 | 97.4M | — | 20 Apr 2026 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 GB8bit | |
| granite-embedding-small-english-r2Open weightsIBM | Apache-2.0 | 47.7M | — | 17 Jul 2025 | — | 0 | ✓ fits0.5 GB4bit✓ fits0.6 GB8bit | |
| granite-guardian-3.3-8bOpen weightsIBM | Apache-2.0 | 8.17B | — | 3 Jun 2025 | — | 0 | ✓ fits5.2 GB4bit✓ fits9.9 GB8bit | |
| granite-speech-4.1-2bOpen weightsIBM | Apache-2.0 | 2.31B | — | 16 Apr 2026 | — | 0 | ✓ fits1.8 GB4bit✓ fits3.2 GB8bit | |
| granite-speech-4.1-2b-narOpen weightsIBM | Apache-2.0 | 2.25B | — | 10 Mar 2026 | — | 0 | ✓ fits1.8 GB4bit✓ fits3.1 GB8bit | |
| granite-speech-4.1-2b-plusOpen weightsIBM | Apache-2.0 | 2.11B | — | 16 Apr 2026 | — | 0 | ✓ fits1.7 GB4bit✓ fits2.9 GB8bit | |
| granite-timeseries-tspulse-r1Open weightsIBM | Apache-2.0 | 1.08M | — | 3 Jun 2025 | — | 0 | ✓ fits0.5 GB4bit✓ fits0.5 GB8bit | |
| granite-timeseries-ttm-r2Open weightsIBM | Apache-2.0 | 805.3K | — | 8 Oct 2024 | — | 0 | ✓ fits0.5 GB4bit✓ fits0.5 GB8bit | |
| granite-vision-3.3-2bOpen weightsIBM | Apache-2.0 | 2.98B | — | 3 Jun 2025 | — | 0 | ✓ fits2.2 GB4bit✓ fits3.9 GB8bit | |
| granite-vision-4.1-4bOpen weightsIBM | Apache-2.0 | 4B | — | 16 Apr 2026 | — | 0 | ✓ fits2.8 GB4bit✓ fits5.1 GB8bit | |
| instructblip-flan-t5-xlOpen weightsSalesforce | MIT | 4.02B | — | 28 May 2023 | — | 0 | ✓ fits2.8 GB4bit✓ fits5.1 GB8bit | |
| internlm-chat-7bOpen weightsInternLM (Shanghai AI Laboratory) | —unclassified | 7B | — | 6 Jul 2023 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.6 GB8bit | |
| internlm-xcomposer-7bOpen weightsInternLM (Shanghai AI Laboratory) | Apache-2.0 | 7B | — | 26 Sept 2023 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.6 GB8bit | |
| internlm-xcomposer2-7bOpen weightsInternLM (Shanghai AI Laboratory) | Other | 7B | — | 25 Jan 2024 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.6 GB8bit | |
| internlm2-1_8bOpen weightsInternLM (Shanghai AI Laboratory) | Other | — | — | 30 Jan 2024 | — | 0 | —— | |
| internlm2-1_8b-rewardOpen weightsInternLM (Shanghai AI Laboratory) | Other | 1.7B | — | 27 Jun 2024 | — | 0 | ✓ fits1.5 GB4bit✓ fits2.5 GB8bit | |
| internlm2-20bOpen weightsInternLM (Shanghai AI Laboratory) | Other | 20B | — | 12 Jan 2024 | — | 0 | ✓ fits12.0 GB4bit✓ fits23.5 GB8bit | |
| internlm2-7bOpen weightsInternLM (Shanghai AI Laboratory) | Other | 7B | — | 12 Jan 2024 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.6 GB8bit | |
| internlm2-base-20bOpen weightsInternLM (Shanghai AI Laboratory) | Other | 20B | — | 12 Jan 2024 | — | 0 | ✓ fits12.0 GB4bit✓ fits23.5 GB8bit | |
| internlm2-base-7bOpen weightsInternLM (Shanghai AI Laboratory) | Other | 7B | — | 12 Jan 2024 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.6 GB8bit | |
| internlm2-chat-20bOpen weightsInternLM (Shanghai AI Laboratory) | Other | 19.9B | — | 10 Jan 2024 | — | 0 | ✓ fits11.9 GB4bit✓ fits23.3 GB8bit | |
| internlm2-chat-7bOpen weightsInternLM (Shanghai AI Laboratory) | Other | 7.74B | — | 10 Jan 2024 | — | 0 | ✓ fits5.0 GB4bit✓ fits9.4 GB8bit | |
| internlm2_5-1_8bOpen weightsInternLM (Shanghai AI Laboratory) | Apache-2.0 | — | — | 31 Jul 2024 | — | 0 | —— | |
| internlm2_5-1_8b-chatOpen weightsInternLM (Shanghai AI Laboratory) | Other | 1.89B | — | 30 Jul 2024 | — | 0 | ✓ fits1.6 GB4bit✓ fits2.7 GB8bit | |
| internlm2_5-7b-chatOpen weightsInternLM (Shanghai AI Laboratory) | Other | 7.74B | — | 27 Jun 2024 | — | 0 | ✓ fits5.0 GB4bit✓ fits9.4 GB8bit | |
| internlm3-8b-instructOpen weightsInternLM (Shanghai AI Laboratory) | Apache-2.0 | 8.8B | — | 13 Jan 2025 | — | 0 | ✓ fits5.6 GB4bit✓ fits10.6 GB8bit | |
| layoutlmv3-baserestricted-weightsMicrosoft | CC-BY-NC-SA-4.0 | 125.3M | — | 18 Apr 2022 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.7 GB8bit | |
| levanter-backpack-1bOpen weightsStanford CRFM | Apache-2.0 | 1.42B | — | 29 May 2023 | — | 0 | ✓ fits1.3 GB4bit✓ fits2.1 GB8bit | |
| levanter-gptOpen weightsStanford CRFM | —unclassified | — | — | 3 Oct 2022 | — | 0 | —— | |
| lmzheng/grok-1Open weightslmzheng | —unclassified | — | — | — | — | 0 | —— | |
| longformer-base-4096Open weightsAllen Institute for AI | Apache-2.0 | — | — | 2 Mar 2022 | — | 0 | —— | |
| m2-bert-80M-2k-retrievalOpen weightsTogether AI | Apache-2.0 | 80M | — | 13 Nov 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 GB8bit | |
| m2-bert-80M-32k-retrievalOpen weightsTogether AI | Apache-2.0 | 80M | — | 4 Nov 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 GB8bit | |
| m2-bert-80M-8k-retrievalOpen weightsTogether AI | Apache-2.0 | 80M | — | 4 Nov 2023 | — | 0 | ✓ fits0.6 GB4bit✓ fits0.6 GB8bit | |
| mdeberta-v3-baseOpen weightsMicrosoft | MIT | — | — | 2 Mar 2022 | — | 0 | —— | |
| mobilebert-uncasedOpen weightsGoogle | Apache-2.0 | — | — | 2 Mar 2022 | — | 0 | —— | |
| mobilevit-smallOpen weightsApple | Other | — | — | 30 May 2022 | — | 0 | —— | |
| mobilevit-xx-smallOpen weightsApple | Other | — | — | 30 May 2022 | — | 0 | —— | |
| mobilevitv2-1.0-imagenet1k-256Open weightsApple | Other | — | — | 5 Jun 2023 | — | 0 | —— | |
| moirai-1.0-R-largerestricted-weightsSalesforce | CC-BY-NC-4.0 | 311M | — | 11 Feb 2024 | — | 0 | ✓ fits0.7 GB4bit✓ fits0.9 GB8bit | |
| moirai-1.0-R-smallrestricted-weightsSalesforce | CC-BY-NC-4.0 | 13.8M | — | 11 Feb 2024 | — | 0 | ✓ fits0.5 GB4bit✓ fits0.5 GB8bit | |
| moirai-1.1-R-largerestricted-weightsSalesforce | CC-BY-NC-4.0 | 311M | — | 14 Jun 2024 | — | 0 | ✓ fits0.7 GB4bit✓ fits0.9 GB8bit | |
| moirai-1.1-R-smallrestricted-weightsSalesforce | CC-BY-NC-4.0 | 13.8M | — | 14 Jun 2024 | — | 0 | ✓ fits0.5 GB4bit✓ fits0.5 GB8bit | |
| moirai-2.0-R-smallrestricted-weightsSalesforce | CC-BY-NC-4.0 | 11.4M | — | 6 Aug 2025 | — | 0 | ✓ fits0.5 GB4bit✓ fits0.5 GB8bit | |
| moirai-moe-1.0-R-baserestricted-weightsSalesforce | CC-BY-NC-4.0 | 935.4M | — | 1 Nov 2024 | — | 0 | ✓ fits1.0 GB4bit✓ fits1.6 GB8bit | |
| music-large-800kOpen weightsStanford CRFM | Apache-2.0 | 780.1M | — | 13 Mar 2024 | — | 0 | ✓ fits0.9 GB4bit✓ fits1.4 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