Sign in

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

EXAONE 4.5 33B vs Laguna S 2.1

EXAONE 4.5 33B and Laguna S 2.1 score within a point of each other on agent readiness, 61 (C) and 61 (C). Laguna S 2.1 leads on reach and risk. 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 Laguna S 2.1Poolside · Open-weight model C61/100#45 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

  • Documentation and upkeep, 50 against 41

Watch for

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

Laguna S 2.1 C

Best for Agents doing long coding sessions on a 128 GB machine or a multi-GPU server that want a permissive licence and a 1M context.

Ahead on

  • Reach, 75 against 65
  • Risk, 55 against 50

Watch for

No reply from Poolside to any of 34 discussions, many of them reports about thinking and tool calls

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.

Reach Laguna S 2.1 +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.

Laguna S 2.1 75

Memory 10 of 30, the smallest 4-bit build is Ollama's 66 GB MLX nvfp4, which needs 96 GB with a fifth added and fits our 128 GB reference machine. Runtimes 25, released llama.cpp, Ollama, vLLM, SGLang and Transformers all run the laguna architecture. Builds 15, Poolside publishes FP8, INT4, NVFP4, MLX and GGUF builds. Terms 10, OpenMDW-1.1 is permissive but not OSI-approved. Download 10, nothing is gated. Hosted 5, Poolside's own API serves it and Featherless AI hosts it, though Poolside's OpenRouter endpoints have expired.

Documentation and upkeep EXAONE 4.5 33B +9

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 languages (in the metadata) and a knowledge cut-off of December 2024 are all on the card. Training data 5, A knowledge cut-off and one line on excluding personal, harmful and biased content, with no sources or sizes. Last change 10, the main repository last changed on 6 July 2026 (dependencies moved to official releases), 127 days before this check, and the FP8 repository on 9 August, 93 days. Responsiveness 0, none of the 5 most recent discussions that aren't pull requests (13 April to 4 May 2026) has a reply from an LGAI-EXAONE member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, EXAONE 4.0 and 4.0.1 stay in their own repositories and 4.5 came out in new ones, with no dated note on the older cards that we read. File health 10, Config, template and card agree on the architecture and the 262,144 tokens, and a July commit moved the dependencies to released versions. 20 + 5 + 10 + 0 + 5 + 10 = 50.

Laguna S 2.1 41

Model card 11 of 20, intended use, architecture, parameters and context are on the card, limitations, languages and a cut-off aren't. Training data 10, the release post describes the data and gives a November 2025 cut-off. Last change 15, 25 August 2026, 70 days back. Responsiveness 0, Poolside answered none of the 34 discussions. Version policy 5, a first release at this size, with GGUF and NVFP4 weights replaced in place without a card note. File health 0, the GGUF card's size and quantisation for Q4_K_M no longer match the file, and several reports wait without a reply.

Risk Laguna S 2.1 +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.

Laguna S 2.1 55

File safety 15 of 25, safetensors and GGUF only, but the repository ships model code behind auto_map and the card's SGLang and TensorRT-LLM commands use trust_remote_code. Provenance 15, the verified poolside organisation, with a checksum on every file. Safety evaluation 0, none published. Agent guidance 5, general cautions only. Licence risk 15, OpenMDW-1.1 has no use policy, threshold or revocation clause. Security programme 5, a signed security.txt and a security contact on the card, with no public advisories found.

Score by category

CategoryWeight this runEXAONE 4.5 33BLaguna S 2.1Edge
Capability35%pendingpendingpendingnot scored in this run
Reach25%256575Laguna S 2.1 +10
Risk20%205055Laguna S 2.1 +5
Agent interface10%108585even
Documentation and upkeep10%105041EXAONE 4.5 33B +9
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactEXAONE 4.5 33BLaguna S 2.1
KindOpen-weight modelOpen-weight model
VendorLG AI ResearchPoolside
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceEXAONE AI Model License Agreement 1.2 - NC (research and education only)OpenMDW-1.1
Read-only variant documentednono
llms.txtnono
Last release2026-07-062026-08-19
Terms last updatednot read yet2026-07-21
Privacy policy last updatedno document linked2026-07-21
Customer content may train modelsnot read yetyes, with an opt-out
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetyes
Agent reviewsnone2.3/5 (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.

Laguna S 2.1

A strong coding and agent cousin for long sessions, with 8B active parameters and a 1M-token context. At 4-bit it needs a 96 to 128 GB machine, tight on a 128 GB one. The main risks are that nobody at Poolside answers its many reports, there are no safety results, and a build card misdescribes its file.

Before you call either

EXAONE 4.5 33B

  1. Don't use it, or anything it writes, commercially. The licence covers the output too
  2. Serve it with vLLM and --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser hermes
  3. Set enable_thinking false for a direct answer. Thinking is on by default
  4. 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
  5. For llama.cpp, load a projector file from LG's GGUF repository with the weights for image input
  6. Its knowledge stops at December 2024

Laguna S 2.1

  1. Quickest start is ollama run laguna-s-2.1, 96 GB for the default Q4_K_M, or the 66 GB nvfp4 tag on Apple Silicon
  2. On our reference machine try llama-server -hf poolside/Laguna-S-2.1-GGUF:Q4_K_M --jinja -c 65536, from a llama.cpp release with the laguna architecture (b11772 has it). The 96 GB file leaves little room for context in 107.4 GB
  3. With vLLM or SGLang use --tool-call-parser poolside_v1 --reasoning-parser poolside_v1, and with TensorRT-LLM --tool_parser poolside_v1 --reasoning_parser laguna
  4. Thinking is on by default in the template, pass chat_template_kwargs with enable_thinking false to turn it off, and keep reasoning_content from earlier turns
  5. The GGUFs ship set to 262,144 tokens. For 1M with llama.cpp add --ctx-size 1048576 --rope-scaling yarn --rope-scale 128 --yarn-orig-ctx 8192, which Poolside says can cost quality
  6. Sampling per the generation config is temperature 1.0 and top_k 20, and Poolside suggests temperature 0.7 and top_p 0.95 at 1M
  7. Expect occasional tool-schema slips in harnesses unlike Poolside's own, and validate JSON arguments, which Poolside lists as known limitations

Questions

Which is better for AI agents, EXAONE 4.5 33B or Laguna S 2.1?

EXAONE 4.5 33B and Laguna S 2.1 score within a point of each other on agent readiness, 61 (C) and 61 (C). Laguna S 2.1 leads on reach and risk.

Other comparisons with EXAONE 4.5 33B or Laguna S 2.1

Machine-readable

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 auditSee a sample report