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=45 | 13032 | 13032 | 13032 | 13032 |
| restricted-weights n=5 | 140 | 302 | 302 | 050 |
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 | |
|---|---|---|---|---|---|---|---|---|
| Olmo-3-1025-7BOpen weightsAllen Institute for AI | Apache-2.0 | 7.3B | — | 12 Sept 2025 | — | 0 | ✓ fits4.7 GB4bit✓ fits8.9 GB8bit | |
| Olmo-3-7B-Instruct-DPOOpen weightsAllen Institute for AI | —unclassified | — | — | — | — | 0 | —— | |
| Olmo-3-7B-Think-DPOOpen weightsAllen Institute for AI | —unclassified | — | — | — | — | 0 | —— | |
| OpenELM-1_1B-Instructrestricted-weightsApple | Apple-AMLR | 1.08B | — | 12 Apr 2024 | — | 0 | ✓ fits1.1 GB4bit✓ fits1.7 GB8bit | |
| OpenELM-270Mrestricted-weightsApple | Apple-AMLR | 271.5M | — | 12 Apr 2024 | — | 0 | ✓ fits0.7 GB4bit✓ fits0.8 GB8bit | |
| Phi-3.5-vision-instructOpen weightsMicrosoft | MIT | 4.15B | — | 16 Aug 2024 | — | 0 | ✓ fits2.9 GB4bit✓ fits5.3 GB8bit | |
| Prompt-Guard-86Mrestricted-weightsMeta AI | Llama-3.1-Community | 278.8M | — | 21 Jul 2024 | — | 0 | ✓ fits0.7 GB4bit✓ fits0.8 GB8bit | |
| Pythia-Chat-Base-7BOpen weightsTogether AI | Apache-2.0 | 7B | — | 22 Mar 2023 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.6 GB8bit | |
| QVQ-72B-PreviewOpen weightsQwen Team · image, text | —unclassified | 72B | — | 25 Dec 2024 | — | 0 | ✓ fits41.9 GB4bit✓ fits83.3 GB8bit | |
| Qianfan-OCROpen weightsBaidu | Apache-2.0 | 4.74B | — | 18 Mar 2026 | — | 0 | ✓ fits3.2 GB4bit✓ fits6.0 GB8bit | |
| Qianfan-VL-3BOpen weightsBaidu | Other | 3.71B | — | 16 Sept 2025 | — | 0 | ✓ fits2.6 GB4bit✓ fits4.8 GB8bit | |
| Qianfan-VL-8BOpen weightsBaidu | Other | 8.81B | — | 16 Sept 2025 | — | 0 | ✓ fits5.6 GB4bit✓ fits10.6 GB8bit | |
| QwQ-Max-PreviewOpen weightsQwen Team · text | Apache-2.0 | — | — | 25 Feb 2025 | — | 0 | —— | |
| Qwen2-AudioOpen weightsQwen Team · audio, text | —unclassified | 7B | — | 9 Aug 2024 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.6 GB8bit | |
| Qwen2-VLOpen weightsQwen Team · image, text, video | Apache-2.0 | — | — | 29 Aug 2024 | — | 0 | —— | |
| Qwen2.5restricted-weightsQwen Team · text | Research-Only | 72.7B70B active | 131.1K | 19 Sept 2024 | — | 0 | ✓ fits42.3 GB4bit✓ fits84.1 GB8bit | |
| Qwen2.5 7B InstructOpen weightsQwen · text | Apache-2.0 | 7.62B | 32.8K | 16 Sept 2024 | — | 1from $0.20 out | ✓ fits4.9 GB4bit✓ fits9.3 GB8bit | |
| Qwen2.5 VLOpen weightsQwen Team · image, text, video | —unclassified | — | — | 26 Jan 2025 | — | 0 | —— | |
| Qwen2.5 VL 72B InstructOpen weightsQwen · image, text | —unclassified | — | 128K | 1 Feb 2025 | — | 1from $1 out | —— | |
| Qwen2.5-0.5BOpen weightsQwen | —unclassified | — | — | — | — | 0 | —— | |
| Qwen2.5-0.5B-InstructOpen weightsQwen | Apache-2.0 | 494M | — | 16 Sept 2024 | — | 0 | ✓ fits0.8 GB4bit✓ fits1.1 GB8bit | |
| Qwen2.5-1.5BOpen weightsQwen | —unclassified | — | — | — | — | 0 | —— | |
| Qwen2.5-1.5B-InstructOpen weightsQwen | Apache-2.0 | 1.54B | — | 17 Sept 2024 | — | 0 | ✓ fits1.4 GB4bit✓ fits2.3 GB8bit | |
| Qwen2.5-1MOpen weightsQwen Team · text | —unclassified | — | 1M | 27 Jan 2025 | — | 0 | —— | |
| Qwen2.5-32BOpen weightsQwen | —unclassified | — | — | — | — | 0 | —— | |
| Qwen2.5-3BOpen weightsQwen | —unclassified | — | — | — | — | 0 | —— | |
| Qwen2.5-3B-InstructOpen weightsQwen | Other | 3.09B | — | 17 Sept 2024 | — | 0 | ✓ fits2.3 GB4bit✓ fits4.0 GB8bit | |
| Qwen2.5-72BOpen weightsQwen | —unclassified | — | — | — | — | 0 | —— | |
| Qwen2.5-7BOpen weightsQwen | —unclassified | — | — | — | — | 0 | —— | |
| Qwen2.5-Coderrestricted-weightsQwen Team · text | Research-Only | 32.5B31B active | 128K | 12 Nov 2024 | — | 0 | ✓ fits19.2 GB4bit✓ fits37.9 GB8bit | |
| Qwen2.5-MathOpen weightsQwen Team · image, text | —unclassified | — | 4.1K | 19 Sept 2024 | — | 0 | —— | |
| Qwen2.5-Math-7BOpen weightsQwen | —unclassified | — | — | — | — | 0 | —— | |
| Qwen2.5-OmniOpen weightsQwen Team · audio, image, text, video | —unclassified | 7B | — | 27 Mar 2025 | — | 0 | ✓ fits4.5 GB4bit✓ fits8.6 GB8bit | |
| Qwen2.5-VL-32B-InstructOpen weightsQwen Team · image, text | Apache-2.0 | 32B | — | 24 Mar 2025 | — | 0 | ✓ fits18.9 GB4bit✓ fits37.3 GB8bit | |
| Qwen2.5-VL-7B-InstructOpen weightsQwen | Apache-2.0 | 8.29B | — | 26 Jan 2025 | — | 0 | ✓ fits5.3 GB4bit✓ fits10.0 GB8bit | |
| Qwen3 235B A22BOpen weightsQwen · text | Apache-2.0 | 235B22B active | 131.1K | 29 Apr 2025 | — | 1from $1.82 out | ✗ too large135.6 GB4bit✗ too large270.8 GB8bit | |
| Qwen3 235B A22B Thinking 2507Open weightsQwen · text | —unclassified | — | 131.1K | 25 Jul 2025 | — | 1from $2.3 out | —— | |
| Qwen3 30B A3BOpen weightsQwen · text | —unclassified | — | 131.1K | 28 Apr 2025 | — | 1from $0.50 out | —— | |
| Qwen3 30B A3B Instruct 2507Open weightsQwen · text | —unclassified | — | 262.1K | 29 Jul 2025 | — | 1from $0.30 out | —— | |
| Qwen3 30B A3B Thinking 2507Open weightsQwen · text | —unclassified | — | 81.9K | 28 Aug 2025 | — | 1from $2.4 out | —— | |
| Qwen3 Coder 480B A35BOpen weightsQwen · text | —unclassified | — | 262.1K | 23 Jul 2025 | — | 1from $1 out | —— | |
| Qwen3 Embedding SeriesOpen weightsQwen Team · embedding, score, text | Apache-2.0 | — | 32.8K | 5 Jun 2025 | — | 0 | —— | |
| Qwen3 Next 80B A3B ThinkingOpen weightsQwen · text | —unclassified | — | 262.1K | 11 Sept 2025 | — | 1from $1.2 out | —— | |
| Qwen3 VL 235B A22B ThinkingOpen weightsQwen · image, text | —unclassified | — | 131.1K | 23 Sept 2025 | — | 1from $4 out | —— | |
| Qwen3 VL 30B A3B ThinkingOpen weightsQwen · image, text | —unclassified | — | 262.1K | 6 Oct 2025 | — | 1from $2.4 out | —— | |
| Qwen3 VL 8B ThinkingOpen weightsQwen · image, text | —unclassified | — | 131.1K | 14 Oct 2025 | — | 1from $2.1 out | —— | |
| Qwen3-0.6B-BaseOpen weightsQwen | —unclassified | — | — | — | — | 0 | —— | |
| Qwen3-4B-BaseOpen weightsQwen | —unclassified | — | — | — | — | 0 | —— | |
| Qwen3-4B-Instruct-2507Open weightsQwen | —unclassified | — | — | — | — | 0 | —— | |
| Qwen3-8B-BaseOpen weightsQwen | —unclassified | — | — | — | — | 0 | —— |
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