Head to head · Open-weight models you run yourself · October 2026 research run

EXAONE 4.5 33B vs ThinkingCap (Qwen3.8 27B)

EXAONE 4.5 33B and ThinkingCap (Qwen3.8 27B) score within a point of each other on agent readiness, 61 (C) and 61 (C). ThinkingCap (Qwen3.8 27B) leads on reach. Both do open-weight models you run yourself.

Best open-weight models you download and run yourself for AI agents · All 6359 open weights comparisons

EXAONE 4.5 33BLG AI Research · Open-weight model C61/100#61 of 160 open-weight models ThinkingCap (Qwen3.8 27B)BottleCap AI · Open-weight model C61/100#58 of 160 open-weight models

Which one, for what

EXAONE 4.5 33B C

Best for Researchers and students working on documents, Korean or multimodal agents who don't need commercial rights

Ahead on

Risk, 50 against 45
Agent interface, 85 against 70

Watch for

Research and education only. No commercial use of the model or its output

ThinkingCap (Qwen3.8 27B) C

Best for Small teams and individuals running Qwen3.8-27B for agent or reasoning work who want shorter thinking traces on one 24 GB GPU or Mac.

Ahead on

Reach, 75 against 65

Watch for

PolyForm Small Business licence, free commercially only below 100 people and 1,000,000 USD (2019) revenue

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Agent interface EXAONE 4.5 33B +15

EXAONE 4.5 33B 85

Chat template 20, chat_template.jinja in the repository (5,930 characters). Tool-calling format 25, the card's vLLM command names the parser, hermes with auto tool choice, and its agentic example calls tools from MCP servers through the OpenAI-compatible API, so declaration and return follow that API. Trained tool calling 20, the card reports agentic tool use among its language results and shows an agent run with several tool servers, and the template renders every call in a turn. Structured output 0, Nothing on the card about JSON or schema-constrained output. Reasoning control 10, enable_thinking is on by default and the card says to set it false for the non-reasoning mode, with an example of each. Context 10, 262,144 tokens per the card's configuration table and config.json, and the card's serve commands run at that length. 20 + 25 + 20 + 0 + 10 + 10 = 85.

ThinkingCap (Qwen3.8 27B) 70

Chat template 20, the same Jinja template as Qwen3.8-27B, in the repository. Tool-calling format 10 of 25, the card names the parsers but the format lives only in the template. Trained tool calling 20, several calls a turn, and BottleCap evaluated agent tasks. Structured output 0, not documented. Reasoning control 10, reasoning_effort budgets thinking per request and the card says where the reasoning comes back. Context 10, 262,144 tokens.

Reach ThinkingCap (Qwen3.8 27B) +10

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. Without the projector, for text only, it would fit 24 GB. Runtimes 15, Released vLLM 0.33.0 has exaone4_5.py, Transformers 5.22.2 has the exaone4_5 model, and llama.cpp b12242 has the architecture, with LG's own GGUF. Three at 5 each. Builds 15, LG publishes GGUF at five quantised precisions, an AWQ build and an FP8 build. Terms 5, Research and educational use only. Download 10, the Hub API reports gated false for all four repositories on 10 November 2026, so the files download with no account and no click-through, though the licence says downloading is acceptance. Hosted 0, Hugging Face maps no inference provider to it, and the card names no API that serves it. 20 + 15 + 15 + 5 + 10 + 0 = 65.

ThinkingCap (Qwen3.8 27B) 75

Memory 25 of 30, BottleCap's IQ4_XS GGUF is 15.5 GB, 18.6 GB with a fifth added, which fits 24 GB. Runtimes 20, it keeps the base's qwen3_5 architecture, which llama.cpp, vLLM, SGLang and Transformers run in released versions, while Ollama's entry is the base's. Builds 15, FP8, NVFP4, MLX and GGUF from BottleCap. Terms 10, PolyForm Small Business is free commercially only below 100 people and 1,000,000 USD (2019) revenue. Download 5, the main repository is gated behind a click-through with an account and contact details, though the GGUF, NVFP4 and MLX builds aren't. Hosted 0, no API or inference provider serves it.

Risk EXAONE 4.5 33B +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. Provenance 15, the files sit in the LGAI-EXAONE organisation (LG AI Research on the Hub), which the card's GitHub repository shares a name with and the licence in the repository is LG's (10). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions: the limitation section lists inappropriate, biased, incorrect and outdated answers and tells users not to try to induce harmful output. Licence risk 5, 15 less 5 for field-of-use limits beyond the law (no commercial use, no building competing models) and 5 for terms the licensor can change or revoke (LG may amend the agreement at any time, and the licence is revocable). Security programme 0, no way to report a flaw on the card beyond a support contact, and www.lgresearch.ai has no security.txt. 25 + 15 + 0 + 5 + 5 + 0 = 50.

ThinkingCap (Qwen3.8 27B) 45

File safety 25, safetensors only and no code in the repository. Provenance 10 of 15, the files are in BottleCap's verified organisation, but the Hub hides the gated files' SHA-256 from the public, so checksums couldn't be confirmed. Safety evaluation 0, none published. Agent guidance 0. Licence risk 10, 5 off for the size and revenue threshold. Security programme 0, no security.txt, disclosure policy or security contact.

Score by category

Category	Weight this run	EXAONE 4.5 33B	ThinkingCap (Qwen3.8 27B)	Edge
Capability	35%pending	pending	pending	not scored in this run
Reach	25%25	65	75	ThinkingCap (Qwen3.8 27B) +10
Risk	20%20	50	45	EXAONE 4.5 33B +5
Agent interface	10%10	85	70	EXAONE 4.5 33B +15
Documentation and upkeep	10%10	50	53	ThinkingCap (Qwen3.8 27B) +3
Negative events	≤15	0	0
Total		C 61/100	C 61/100

Facts side by side

Fact	EXAONE 4.5 33B	ThinkingCap (Qwen3.8 27B)
Kind	Open-weight model	Open-weight model
Vendor	LG AI Research	BottleCap AI
Hosted endpoint	no (local only)	no (local only)
Transports
Auth	None	None
Pricing	Free	Free
x402	no	no
Licence	EXAONE AI Model License Agreement 1.2 - NC (research and education only)	PolyForm-Small-Business-1.0.0
Read-only variant documented	no	no
llms.txt	no	no
Last release	2026-07-06	2026-10-06
Terms last updated	not read yet	no document linked
Privacy policy last updated	no document linked	2026-01-21
Agent reviews	none	2.5/5 (4)

Verdicts

EXAONE 4.5 33B

A well-documented vision-language model with a full set of builds, tool calling, switchable reasoning, a 256K context and a stated knowledge cut-off. The licence decides whether you can use it: research and education only, output included, and LG can change the terms. Nothing answered on the repository and no safety results.

ThinkingCap (Qwen3.8 27B)

A Qwen3.8-27B with shorter reasoning, for agent work where thinking tokens cost time, and BottleCap's 4-bit GGUF runs in about 19 GB. The main limits are the licence, which needs a paid licence above 100 people or 1,000,000 USD revenue, a gated main repository, and no safety results or training-data description.

Before you call either

EXAONE 4.5 33B

Don't use it, or anything it writes, commercially. The licence covers the output too
Serve it with vLLM and --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser hermes
Set enable_thinking false for a direct answer. Thinking is on by default
Use temperature 1.0, top_p 0.95 and presence_penalty 1.5 in general, and temperature 0.6 with top_k 20 for documents and Korean
For llama.cpp, load a projector file from LG's GGUF repository with the weights for image input
Its knowledge stops at December 2024

ThinkingCap (Qwen3.8 27B)

Check the licence first, an organisation with 100 or more people or 1,000,000 USD (2019) revenue needs a commercial licence from BottleCap
For files without the gate use llama-server -hf bottlecapai/ThinkingCap-Qwen3.8-27B-GGUF:Q4_K_M --jinja, about 17.4 GB
On vLLM use --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_xml, and on SGLang --tool-call-parser qwen3_coder
Set reasoning_effort (xhigh, medium or low) in chat_template_kwargs, any other value makes the template raise an error
Keep the base's sampling (temperature 1.0, top_p 0.95, top_k 20), the GGUF card says greedy decoding can loop
The GGUFs carry an MTP head, and llama.cpp builds without MTP support for this architecture may refuse to load them with a missing blk.64 tensor

Questions

Which is better for AI agents, EXAONE 4.5 33B or ThinkingCap (Qwen3.8 27B)?

EXAONE 4.5 33B and ThinkingCap (Qwen3.8 27B) score within a point of each other on agent readiness, 61 (C) and 61 (C). ThinkingCap (Qwen3.8 27B) leads on reach.

Other comparisons with EXAONE 4.5 33B or ThinkingCap (Qwen3.8 27B)

Machine-readable

This page as Markdown /compare/exaone-4-5-33b-vs-thinkingcap-qwen3-8-27b.md · slim .min.md · JSON .json (or send Accept: text/markdown)
Each listing in full /api/v1/tools/exaone-4-5-33b.json · /api/v1/tools/thinkingcap-qwen3-8-27b.json
From a terminal anchor compare exaone-4-5-33b thinkingcap-qwen3-8-27b (the CLI)
Over MCP compare_tools {"a": "exaone-4-5-33b", "b": "thinkingcap-qwen3-8-27b"} at /mcp, no key

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an audit See a sample report