Skip to content
AI Atlas
Open model frontier

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.

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 pageCommercial useRedistributionDerivativesHosting
Open source n=0
Open weights n=4325018250182501825018
restricted-weights n=7070700700070

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

ModelLicence · permissionsParamsContextReleaseBest resultsProvidersFit 64 GB @4bit · 128 GB @8bit Estimated
granite-4.0-1b-baseOpen weightsIBMunclassified0
granite-docling-258MOpen weightsIBMApache-2.0257.5M19 May 20250✓ fits0.7 GB4bit✓ fits0.8 GB8bit
granite-embedding-125m-englishOpen weightsIBMApache-2.0124.7M4 Dec 20240✓ fits0.6 GB4bit✓ fits0.6 GB8bit
granite-embedding-311m-multilingual-r2Open weightsIBMApache-2.0311.7M20 Apr 20260✓ fits0.7 GB4bit✓ fits0.9 GB8bit
granite-embedding-97m-multilingual-r2Open weightsIBMApache-2.097.4M20 Apr 20260✓ fits0.6 GB4bit✓ fits0.6 GB8bit
granite-embedding-small-english-r2Open weightsIBMApache-2.047.7M17 Jul 20250✓ fits0.5 GB4bit✓ fits0.6 GB8bit
granite-guardian-3.3-8bOpen weightsIBMApache-2.08.17B3 Jun 20250✓ fits5.2 GB4bit✓ fits9.9 GB8bit
granite-speech-4.1-2bOpen weightsIBMApache-2.02.31B16 Apr 20260✓ fits1.8 GB4bit✓ fits3.2 GB8bit
granite-speech-4.1-2b-narOpen weightsIBMApache-2.02.25B10 Mar 20260✓ fits1.8 GB4bit✓ fits3.1 GB8bit
granite-speech-4.1-2b-plusOpen weightsIBMApache-2.02.11B16 Apr 20260✓ fits1.7 GB4bit✓ fits2.9 GB8bit
granite-timeseries-tspulse-r1Open weightsIBMApache-2.01.08M3 Jun 20250✓ fits0.5 GB4bit✓ fits0.5 GB8bit
granite-timeseries-ttm-r2Open weightsIBMApache-2.0805.3K8 Oct 20240✓ fits0.5 GB4bit✓ fits0.5 GB8bit
granite-vision-3.3-2bOpen weightsIBMApache-2.02.98B3 Jun 20250✓ fits2.2 GB4bit✓ fits3.9 GB8bit
granite-vision-4.1-4bOpen weightsIBMApache-2.04B16 Apr 20260✓ fits2.8 GB4bit✓ fits5.1 GB8bit
instructblip-flan-t5-xlOpen weightsSalesforceMIT4.02B28 May 20230✓ fits2.8 GB4bit✓ fits5.1 GB8bit
internlm-chat-7bOpen weightsInternLM (Shanghai AI Laboratory)unclassified7B6 Jul 20230✓ fits4.5 GB4bit✓ fits8.6 GB8bit
internlm-xcomposer-7bOpen weightsInternLM (Shanghai AI Laboratory)Apache-2.07B26 Sept 20230✓ fits4.5 GB4bit✓ fits8.6 GB8bit
internlm-xcomposer2-7bOpen weightsInternLM (Shanghai AI Laboratory)Other7B25 Jan 20240✓ fits4.5 GB4bit✓ fits8.6 GB8bit
internlm2-1_8bOpen weightsInternLM (Shanghai AI Laboratory)Other30 Jan 20240
internlm2-1_8b-rewardOpen weightsInternLM (Shanghai AI Laboratory)Other1.7B27 Jun 20240✓ fits1.5 GB4bit✓ fits2.5 GB8bit
internlm2-20bOpen weightsInternLM (Shanghai AI Laboratory)Other20B12 Jan 20240✓ fits12.0 GB4bit✓ fits23.5 GB8bit
internlm2-7bOpen weightsInternLM (Shanghai AI Laboratory)Other7B12 Jan 20240✓ fits4.5 GB4bit✓ fits8.6 GB8bit
internlm2-base-20bOpen weightsInternLM (Shanghai AI Laboratory)Other20B12 Jan 20240✓ fits12.0 GB4bit✓ fits23.5 GB8bit
internlm2-base-7bOpen weightsInternLM (Shanghai AI Laboratory)Other7B12 Jan 20240✓ fits4.5 GB4bit✓ fits8.6 GB8bit
internlm2-chat-20bOpen weightsInternLM (Shanghai AI Laboratory)Other19.9B10 Jan 20240✓ fits11.9 GB4bit✓ fits23.3 GB8bit
internlm2-chat-7bOpen weightsInternLM (Shanghai AI Laboratory)Other7.74B10 Jan 20240✓ fits5.0 GB4bit✓ fits9.4 GB8bit
internlm2_5-1_8bOpen weightsInternLM (Shanghai AI Laboratory)Apache-2.031 Jul 20240
internlm2_5-1_8b-chatOpen weightsInternLM (Shanghai AI Laboratory)Other1.89B30 Jul 20240✓ fits1.6 GB4bit✓ fits2.7 GB8bit
internlm2_5-7b-chatOpen weightsInternLM (Shanghai AI Laboratory)Other7.74B27 Jun 20240✓ fits5.0 GB4bit✓ fits9.4 GB8bit
internlm3-8b-instructOpen weightsInternLM (Shanghai AI Laboratory)Apache-2.08.8B13 Jan 20250✓ fits5.6 GB4bit✓ fits10.6 GB8bit
layoutlmv3-baserestricted-weightsMicrosoftCC-BY-NC-SA-4.0125.3M18 Apr 20220✓ fits0.6 GB4bit✓ fits0.7 GB8bit
levanter-backpack-1bOpen weightsStanford CRFMApache-2.01.42B29 May 20230✓ fits1.3 GB4bit✓ fits2.1 GB8bit
levanter-gptOpen weightsStanford CRFMunclassified3 Oct 20220
lmzheng/grok-1Open weightslmzhengunclassified0
longformer-base-4096Open weightsAllen Institute for AIApache-2.02 Mar 20220
m2-bert-80M-2k-retrievalOpen weightsTogether AIApache-2.080M13 Nov 20230✓ fits0.6 GB4bit✓ fits0.6 GB8bit
m2-bert-80M-32k-retrievalOpen weightsTogether AIApache-2.080M4 Nov 20230✓ fits0.6 GB4bit✓ fits0.6 GB8bit
m2-bert-80M-8k-retrievalOpen weightsTogether AIApache-2.080M4 Nov 20230✓ fits0.6 GB4bit✓ fits0.6 GB8bit
mdeberta-v3-baseOpen weightsMicrosoftMIT2 Mar 20220
mobilebert-uncasedOpen weightsGoogleApache-2.02 Mar 20220
mobilevit-smallOpen weightsAppleOther30 May 20220
mobilevit-xx-smallOpen weightsAppleOther30 May 20220
mobilevitv2-1.0-imagenet1k-256Open weightsAppleOther5 Jun 20230
moirai-1.0-R-largerestricted-weightsSalesforceCC-BY-NC-4.0311M11 Feb 20240✓ fits0.7 GB4bit✓ fits0.9 GB8bit
moirai-1.0-R-smallrestricted-weightsSalesforceCC-BY-NC-4.013.8M11 Feb 20240✓ fits0.5 GB4bit✓ fits0.5 GB8bit
moirai-1.1-R-largerestricted-weightsSalesforceCC-BY-NC-4.0311M14 Jun 20240✓ fits0.7 GB4bit✓ fits0.9 GB8bit
moirai-1.1-R-smallrestricted-weightsSalesforceCC-BY-NC-4.013.8M14 Jun 20240✓ fits0.5 GB4bit✓ fits0.5 GB8bit
moirai-2.0-R-smallrestricted-weightsSalesforceCC-BY-NC-4.011.4M6 Aug 20250✓ fits0.5 GB4bit✓ fits0.5 GB8bit
moirai-moe-1.0-R-baserestricted-weightsSalesforceCC-BY-NC-4.0935.4M1 Nov 20240✓ fits1.0 GB4bit✓ fits1.6 GB8bit
music-large-800kOpen weightsStanford CRFMApache-2.0780.1M13 Mar 20240✓ 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