# Apertus v1.5 8B vs EXAONE 4.5 33B (slim)

> Apertus v1.5 8B and EXAONE 4.5 33B score within a point of each other for open-weight models you run yourself, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-exaone-4-5-33b.md (~9,400 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-exaone-4-5-33b.json · canonical https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-exaone-4-5-33b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Apertus v1.5 8B and EXAONE 4.5 33B score within a point of each other on agent readiness, 61 (C) and 61 (C). EXAONE 4.5 33B leads on reach. Both do open-weight models you run yourself.

- Apertus v1.5 8B: C 61, rank #40 of 160 open-weight models · https://www.anchorterminal.com/tools/apertus-v1-5-8b.min.md
- EXAONE 4.5 33B: C 61, rank #61 of 160 open-weight models · https://www.anchorterminal.com/tools/exaone-4-5-33b.min.md
- Apertus v1.5 8B, good for Agents that want a fully open, multilingual 8B with image and audio input on one 24 GB GPU, and can run a publisher fork of vLLM. Ahead on Risk, 75 against 50; Documentation and upkeep, 84 against 50.
- EXAONE 4.5 33B, good for Researchers and students working on documents, Korean or multimodal agents who don't need commercial rights Ahead on Reach, 65 against 40.

| Category | Apertus v1.5 8B | EXAONE 4.5 33B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 40 | 65 |
| Risk (20%) | 75 | 50 |
| Agent interface (10%) | 85 | 85 |
| Documentation and upkeep (10%) | 84 | 50 |

| Fact (where they differ) | Apertus v1.5 8B | EXAONE 4.5 33B |
| --- | --- | --- |
| Vendor | Swiss AI Initiative (EPFL and ETH Zurich) | LG AI Research |
| Licence | Apache-2.0, with the Apertus Acceptable Use Policy (v1.5, 14 July 2026) accepted at the download gate | EXAONE AI Model License Agreement 1.2 - NC (research and education only) |
| Last release | 2026-10-14 | 2026-07-06 |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Documentation and upkeep, Apertus v1.5 8B +34: Apertus v1.5 8B 84 (Model card 14 of 20, languages and a knowledge cut-off are missing.); EXAONE 4.5 33B 50 (Model card 20, Uses (the quickstart's question answering, document and agent examples), limitations, the architecture, the parameters, the context, the language…)
- Reach, EXAONE 4.5 33B +25: Apertus v1.5 8B 40 (Memory 25 of 30, the BF16 files are 18.4 GB, or 22.1 GB with a fifth added, which fits 24 GB.); EXAONE 4.5 33B 65 (Memory 20, the smallest build at 4 bits is LG's IQ4_XS GGUF, 18.03 GB with the 2.57 GB projector, and 20.60 GB × 1.2 = 24.7 GB, within 32 GB.)
- Risk, Apertus v1.5 8B +25: Apertus v1.5 8B 75 (File safety 25, safetensors only and no code in the repository.); EXAONE 4.5 33B 50 (File safety 25, safetensors and GGUF only, no .bin, .pt or .pth files and no Python in the repository.)