# EXAONE 4.5 33B vs Qwen3-VL-2B-Instruct (slim)

> EXAONE 4.5 33B and Qwen3-VL-2B-Instruct 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/exaone-4-5-33b-vs-qwen3-vl-2b-instruct.md (~9,950 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-qwen3-vl-2b-instruct.json · canonical https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-qwen3-vl-2b-instruct
- 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)

EXAONE 4.5 33B and Qwen3-VL-2B-Instruct score within a point of each other on agent readiness, 61 (C) and 61 (C). Qwen3-VL-2B-Instruct leads on reach and risk. Both do open-weight models you run yourself.

- EXAONE 4.5 33B: C 61, rank #61 of 160 open-weight models · https://www.anchorterminal.com/tools/exaone-4-5-33b.min.md
- Qwen3-VL-2B-Instruct: C 61, rank #52 of 160 open-weight models · https://www.anchorterminal.com/tools/qwen3-vl-2b-instruct.min.md
- EXAONE 4.5 33B, good for Researchers and students working on documents, Korean or multimodal agents who don't need commercial rights Ahead on Agent interface, 85 against 60; Documentation and upkeep, 50 against 31.
- Qwen3-VL-2B-Instruct, good for An agent on a laptop or small edge device that needs a local model to read images, documents and video in about 2 GB Ahead on Reach, 95 against 65; Risk, 55 against 50.

| Category | EXAONE 4.5 33B | Qwen3-VL-2B-Instruct |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 95 |
| Risk (20%) | 50 | 55 |
| Agent interface (10%) | 85 | 60 |
| Documentation and upkeep (10%) | 50 | 31 |

| Fact (where they differ) | EXAONE 4.5 33B | Qwen3-VL-2B-Instruct |
| --- | --- | --- |
| Vendor | LG AI Research | Alibaba (Qwen team) |
| Licence | EXAONE AI Model License Agreement 1.2 - NC (research and education only) | Apache-2.0 |
| Last release | 2026-07-06 | 2025-11-01 |
| Terms last updated | not read yet | no document linked |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Reach, Qwen3-VL-2B-Instruct +30: 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.); Qwen3-VL-2B-Instruct 95 (Alibaba's own Q4_K_M GGUF with its vision file is 1.56 GB, so with a fifth added it needs about 1.9 GB and fits well within 16 GB (30).)
- Agent interface, EXAONE 4.5 33B +25: EXAONE 4.5 33B 85 (Chat template 20, chat_template.jinja in the repository (5,930 characters).); Qwen3-VL-2B-Instruct 60 (A Jinja chat template in the repository (20).)
- Documentation and upkeep, EXAONE 4.5 33B +19: 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…); Qwen3-VL-2B-Instruct 31 (The card misses limitations, languages and a cut-off (11).)
- Risk, Qwen3-VL-2B-Instruct +5: EXAONE 4.5 33B 50 (File safety 25, safetensors and GGUF only, no .bin, .pt or .pth files and no Python in the repository.); Qwen3-VL-2B-Instruct 55 (Safetensors and GGUF only and no code in the repositories, so the FP8 card's trust_remote_code flag runs nothing (25).)