# Apertus v1.5 8B vs Cola2 (slim)

> Apertus v1.5 8B scores 61 (C) to Cola2's 33.9 (F) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-cola2.md (~8,950 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-cola2.json · canonical https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-cola2
- 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 scores 61 (C) on agent readiness against Cola2's 33.9 (F), and leads in every scored category. 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
- Cola2: F 33.9, rank #160 of 160 open-weight models · https://www.anchorterminal.com/tools/cola2.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 Reach, 40 against 25; Risk, 75 against 40; Agent interface, 85 against 20; Documentation and upkeep, 84 against 58.
- Cola2, good for Researchers working on latent or diffusion language models who want a checkpoint to study

| Category | Apertus v1.5 8B | Cola2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 40 | 25 |
| Risk (20%) | 75 | 40 |
| Agent interface (10%) | 85 | 20 |
| Documentation and upkeep (10%) | 84 | 58 |

| Fact (where they differ) | Apertus v1.5 8B | Cola2 |
| --- | --- | --- |
| Vendor | Swiss AI Initiative (EPFL and ETH Zurich) | ByteDance (Seed) |
| Licence | Apache-2.0, with the Apertus Acceptable Use Policy (v1.5, 14 July 2026) accepted at the download gate | None stated for the weights (the code is Apache 2.0) |
| Last release | 2026-10-14 | 2026-11-06 |
| Terms last updated | not read yet | no document linked |
| Agent reviews | 2.8/5 (4) | none |

Why the edge:
- Agent interface, Apertus v1.5 8B +65: Apertus v1.5 8B 85 (Chat template 20, a Jinja file in the repository.); Cola2 20 (Chat template 20, A chat template in tokenizer_config.json (4,116 characters), which came with the Qwen3 tokenizer.)
- Risk, Apertus v1.5 8B +35: Apertus v1.5 8B 75 (File safety 25, safetensors only and no code in the repository.); Cola2 40 (File safety 15, safetensors only, no .bin, .pt or .pth files (25).)
- Documentation and upkeep, Apertus v1.5 8B +26: Apertus v1.5 8B 84 (Model card 14 of 20, languages and a knowledge cut-off are missing.); Cola2 58 (Model card 8, Intended use and limitations (the out-of-scope list, and the unconverged latent model) and the architecture are on the card and the GitHub model c…)
- Reach, Apertus v1.5 8B +15: 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.); Cola2 25 (Memory 15, the only build is the F32 safetensors set, 35.07 GB, and 35.07 GB × 1.2 = 42.1 GB, within 64 GB.)