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 | 24019 | 24019 | 24019 | 24019 |
| restricted-weights n=7 | 430 | 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 | |
|---|---|---|---|---|---|---|---|---|
| Mistral-7B-Instruct-v0.1Open weightsMistral AI | Apache-2.0 | 7.24B | — | 27 Sept 2023 | — | 0 | ✓ fits4.7 GB4bit✓ fits8.8 GB8bit | |
| Mistral-7B-Instruct-v0.2Open weightsMistral AI | Apache-2.0 | 7.24B | — | 11 Dec 2023 | — | 0 | ✓ fits4.7 GB4bit✓ fits8.8 GB8bit | |
| Mistral-7B-Instruct-v0.3Open weightsMistral AI | Apache-2.0 | 7.25B | — | 22 May 2024 | — | 0 | ✓ fits4.7 GB4bit✓ fits8.8 GB8bit | |
| Mistral-7B-v0.1Open weightsMistral AI | Apache-2.0 | 7.24B | — | 20 Sept 2023 | — | 0 | ✓ fits4.7 GB4bit✓ fits8.8 GB8bit | |
| Mistral-7B-v0.3Open weightsMistral AI | Apache-2.0 | 7.25B | — | 22 May 2024 | — | 0 | ✓ fits4.7 GB4bit✓ fits8.8 GB8bit | |
| Mistral-Medium-3.5-128BOpen weightsMistral AI | Other | 127.7B | — | 31 Mar 2026 | — | 0 | ✗ too large73.9 GB4bit✗ too large147.4 GB8bit | |
| Mistral-Nemo-Base-2407Open weightsMistral AI | Apache-2.0 | 12.3B | — | 18 Jul 2024 | — | 0 | ✓ fits7.5 GB4bit✓ fits14.6 GB8bit | |
| Mistral-Small-24B-Base-2501Open weightsMistral AI | —unclassified | — | — | — | — | 0 | —— | |
| Mistral-Small-3.1-24B-Base-2503Open weightsMistral AI | —unclassified | — | — | — | — | 0 | —— | |
| Mixtral 8x22B InstructOpen weightsMistral AI · text | —unclassified | — | 65.5K | 17 Apr 2024 | — | 1from $6 out | —— | |
| Mixtral-8x7B-Instruct-v0.1Open weightsMistral AI | Apache-2.0 | 46.7B | — | 10 Dec 2023 | — | 0 | ✓ fits27.4 GB4bit✓ fits54.2 GB8bit | |
| Mixtral-8x7B-v0.1Open weightsMistral AI | —unclassified | — | — | — | — | 0 | —— | |
| MobileCLIP-S1-OpenCLIPrestricted-weightsApple | Apple-AMLR | — | — | 7 Jun 2024 | — | 0 | —— | |
| MobileCLIP-S2-OpenCLIPrestricted-weightsApple | Apple-AMLR | — | — | 7 Jun 2024 | — | 0 | —— | |
| Molmo2-4BOpen weightsAllen Institute for AI | Apache-2.0 | 4.85B | — | 14 Dec 2025 | — | 0 | ✓ fits3.3 GB4bit✓ fits6.1 GB8bit | |
| MoonViT-SO-400MOpen weightsMoonshot AI | MIT | 416.9M | — | 10 Apr 2025 | — | 0 | ✓ fits0.7 GB4bit✓ fits1.0 GB8bit | |
| Moonlight-16B-A3BOpen weightsMoonshot AI | MIT | 16B3B active | — | 22 Feb 2025 | — | 0 | ✓ fits9.7 GB4bit✓ fits18.9 GB8bit | |
| Moonlight-16B-A3B-InstructOpen weightsMoonshot AI | MIT | 16B3B active | — | 22 Feb 2025 | — | 0 | ✓ fits9.7 GB4bit✓ fits18.9 GB8bit | |
| MythoMax 13BOpen weightsgryphe · text | —unclassified | — | 8.19K | 2 Jul 2023 | — | 1from $0.06 out | —— | |
| Nemotron 3 Nano Omni (free)Open weightsNVIDIA | —unclassified | — | — | — | — | 1 | —— | |
| Nemotron 3.5 Content SafetyOpen weightsNVIDIA · image, text | —unclassified | — | 131.1K | 4 Jun 2026 | — | 1from $0.20 out | —— | |
| Nex-N2.5-Mini (free)Open weightsNex AGI | —unclassified | — | — | — | — | 1 | —— | |
| Nex-N2.5-Pro (free)Open weightsNex AGI | —unclassified | — | — | — | — | 1 | —— | |
| North Small Translaterestricted-weightsCohere · text | CC-BY-NC-4.0 | 218B25B active | 16K | 10 Sept 2026 | — | 0 | ✗ too large125.8 GB4bit✗ too large251.2 GB8bit | |
| North-Micro-Vision-InstructOpen weightsCohere | Apache-2.0 | 2.48B | — | 10 Aug 2026 | — | 0 | ✓ fits1.9 GB4bit✓ fits3.4 GB8bit | |
| Nous-Hermes-2-Mixtral-8x7B-DPOOpen weightsNous Research | Apache-2.0 | 46.7B | — | 11 Jan 2024 | — | 0 | ✓ fits27.4 GB4bit✓ fits54.2 GB8bit | |
| Nous-Hermes-2-SOLAR-10.7BOpen weightsNous Research | Apache-2.0 | 10.7B | — | 1 Jan 2024 | — | 0 | ✓ fits6.7 GB4bit✓ fits12.8 GB8bit | |
| Nous-Hermes-2-Yi-34BOpen weightsNous Research | Apache-2.0 | 34.4B | — | 23 Dec 2023 | — | 0 | ✓ fits20.3 GB4bit✓ fits40.0 GB8bit | |
| Nous-Hermes-llama-2-7bOpen weightsNous Research | MIT | 6.74B | — | 25 Jul 2023 | — | 0 | ✓ fits4.4 GB4bit✓ fits8.3 GB8bit | |
| NousResearch/Llama-2-7b-chat-hfOpen weightsNous Research | —unclassified | 6.74B | — | 18 Jul 2023 | — | 0 | ✓ fits4.4 GB4bit✓ fits8.3 GB8bit | |
| NousResearch/Llama-2-7b-hfOpen weightsNous Research | —unclassified | 6.74B | — | 18 Jul 2023 | — | 0 | ✓ fits4.4 GB4bit✓ fits8.3 GB8bit | |
| NousResearch/Llama-3.2-1Brestricted-weightsNous Research | Llama-3.2-Community | 1.24B | — | 27 Sept 2024 | — | 0 | ✓ fits1.2 GB4bit✓ fits1.9 GB8bit | |
| NousResearch/Meta-Llama-3-70B-InstructOpen weightsNous Research | Other | 70.5B | — | 19 Apr 2024 | — | 0 | ✓ fits41.1 GB4bit✓ fits81.6 GB8bit | |
| NousResearch/Meta-Llama-3-8BOpen weightsNous Research | Other | 8.03B | — | 18 Apr 2024 | — | 0 | ✓ fits5.1 GB4bit✓ fits9.7 GB8bit | |
| NousResearch/Meta-Llama-3-8B-InstructOpen weightsNous Research | Other | 8.03B | — | 18 Apr 2024 | — | 0 | ✓ fits5.1 GB4bit✓ fits9.7 GB8bit | |
| NousResearch/Meta-Llama-3.1-70B-Instructrestricted-weightsNous Research | Llama-3.1-Community | 70.5B | — | 24 Jul 2024 | — | 0 | ✓ fits41.1 GB4bit✓ fits81.6 GB8bit | |
| NousResearch/Meta-Llama-3.1-8Brestricted-weightsNous Research | Llama-3.1-Community | 8.03B | — | 24 Jul 2024 | — | 0 | ✓ fits5.1 GB4bit✓ fits9.7 GB8bit | |
| NousResearch/Meta-Llama-3.1-8B-Instructrestricted-weightsNous Research | Llama-3.1-Community | 8.03B | — | 24 Jul 2024 | — | 0 | ✓ fits5.1 GB4bit✓ fits9.7 GB8bit | |
| OLMo-1B-hfOpen weightsAllen Institute for AI | Apache-2.0 | 1.18B | — | 12 Apr 2024 | — | 0 | ✓ fits1.2 GB4bit✓ fits1.9 GB8bit | |
| OLMo-2-0325-32B-DPOOpen weightsAllen Institute for AI | —unclassified | — | — | — | — | 0 | —— | |
| OLMo-2-0325-32B-InstructOpen weightsAllen Institute for AI | Apache-2.0 | 32.2B | — | 12 Mar 2025 | — | 0 | ✓ fits19.0 GB4bit✓ fits37.6 GB8bit | |
| OLMo-2-0425-1BOpen weightsAllen Institute for AI | Apache-2.0 | 1.48B | — | 17 Apr 2025 | — | 0 | ✓ fits1.4 GB4bit✓ fits2.2 GB8bit | |
| OLMo-2-0425-1B-InstructOpen weightsAllen Institute for AI | Apache-2.0 | 1.48B | — | 29 Apr 2025 | — | 0 | ✓ fits1.4 GB4bit✓ fits2.2 GB8bit | |
| OLMo-2-0425-1B-RLVR1Open weightsAllen Institute for AI | —unclassified | — | — | — | — | 0 | —— | |
| OLMo-2-1124-7BOpen weightsAllen Institute for AI | Apache-2.0 | 7.3B | — | 29 Oct 2024 | — | 0 | ✓ fits4.7 GB4bit✓ fits8.9 GB8bit | |
| OLMo-2-1124-7B-DPOOpen weightsAllen Institute for AI | —unclassified | — | — | — | — | 0 | —— | |
| OLMo-2-1124-7B-InstructOpen weightsAllen Institute for AI | Apache-2.0 | 7.3B | — | 18 Dec 2024 | — | 0 | ✓ fits4.7 GB4bit✓ fits8.9 GB8bit | |
| OLMoE-1B-7B-0125-DPOOpen weightsAllen Institute for AI | —unclassified | — | — | — | — | 0 | —— | |
| OLMoE-1B-7B-0125-InstructOpen weightsAllen Institute for AI | Apache-2.0 | 6.92B | — | 27 Jan 2025 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.5 GB8bit | |
| OLMoE-1B-7B-0924Open weightsAllen Institute for AI | Apache-2.0 | 6.92B | — | 20 Jul 2024 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.5 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