Sign in

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

EXAONE 4.5 33B vs Kronos

EXAONE 4.5 33B scores 61 (C) on agent readiness against Kronos's 55.2 (C), and leads in 2 of 4 scored categories. Kronos leads on documentation and upkeep. 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 KronosYu Shi (shiyu-coder, NeoQuasar), Tsinghua University · Open-weight model C55.2/100#122 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

  • Reach, 65 against 55
  • Agent interface, 85 against 60

Watch for

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

Kronos C

Best for Agents that need a quick local forecast or synthetic sample of a candlestick series on modest hardware, for research or as one input among others.

Ahead on

  • Documentation and upkeep, 61 against 50

Watch for

Runs only through the publisher's own PyTorch code from GitHub, in no named runtime and with no quantised build

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 +25

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.

Kronos 60

Read for a forecasting model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. The card documents the DataFrame and timestamps it takes and the DataFrame it returns, and the publisher's KronosPredictor builds and parses them (25). It was trained on six K-line fields with calendar fields, one series per forecast (10). Output is a typed DataFrame indexed by the requested timestamps, the mean of the sampled paths (15). The input format is given only as code (10). Reasoning control and context score 0, with no reasoning and a 512-bar context (2,048 for Kronos-mini).

Documentation and upkeep Kronos +11

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.

Kronos 61

Model card 11, intended use, architecture, parameters and context are there, limitations, languages and a cut-off aren't. Training data 20, the paper lists every exchange with asset and observation counts, the filtering and a June 2024 end. Last change 5, the reference code on 13 April 2026 (still the newest commit on 4 November, 205 days) and the Hub repositories on 9 September 2025. Responsiveness 20, the publisher answered 10 of 18 Hugging Face discussions (recounted by script on 4 November), though none since 24 November 2025, and the seven opened since April 2026 have no reply from it. Version policy 5, a first release. File health 0, the cards point to example data the repository has deleted and to licence and requirements links on a branch that doesn't exist.

Reach EXAONE 4.5 33B +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.

Kronos 55

Memory 30, the publisher's Kronos-mini with its tokeniser is 0.03 GB and even Kronos-base is 0.43 GB in FP32. Runtimes 0, it runs only through the publisher's own PyTorch package from GitHub, and none of the six named runtimes supports it. Builds 0, FP32 safetensors only. Terms 15, MIT with nothing added. Download 10, nothing is gated. Hosted 0, no inference provider or publisher API serves it (provider mapping still empty on 4 November).

Score by category

CategoryWeight this runEXAONE 4.5 33BKronosEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%256555EXAONE 4.5 33B +10
Risk20%205050even
Agent interface10%108560EXAONE 4.5 33B +25
Documentation and upkeep10%105061Kronos +11
Negative events≤1500
TotalC 61/100C 55.2/100

Facts side by side

FactEXAONE 4.5 33BKronos
KindOpen-weight modelOpen-weight model
VendorLG AI ResearchYu Shi (shiyu-coder, NeoQuasar), Tsinghua University
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceEXAONE AI Model License Agreement 1.2 - NC (research and education only)MIT
Read-only variant documentednono
llms.txtnono
Last release2026-07-062026-04-13
Terms last updatednot read yetno document linked
Privacy policy last updatedno document linkedno document linked
Popularitynone43k stars

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.

Kronos

Forecasts the next price bars from a history of up to 512 candlestick bars. Every size fits in under 0.5 GB and runs on a CPU, but only through the publisher's own Python package. Nobody has benchmarked it independently, its quickstart data was deleted from the repository, and the publisher hasn't replied since November 2025.

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

Kronos

  1. Clone https://github.com/shiyu-coder/Kronos and pip install -r requirements.txt, then load Kronos.from_pretrained("NeoQuasar/Kronos-small") and KronosTokenizer.from_pretrained("NeoQuasar/Kronos-Tokenizer-base") and wrap them in KronosPredictor
  2. Pair Kronos-mini with Kronos-Tokenizer-2k and Kronos-small or Kronos-base with Kronos-Tokenizer-base, the cards' pairing
  3. The examples read examples/data/XSHG_5min_600977.csv, which no longer exists; point them at tests/data/regression_input.csv, 2,500 five-minute bars
  4. Keep the lookback at or under max_context, 512 bars, and pass the future timestamps you want as y_timestamp, since the calendar fields come from them
  5. Raise sample_count for a steadier forecast, but expect only the mean back; call the lower-level auto_regressive_inference yourself if you need the paths
  6. Treat forecasts as model output to check, not signals; the README says its own backtest pipeline isn't a production trading system

Questions

Which is better for AI agents, EXAONE 4.5 33B or Kronos?

EXAONE 4.5 33B scores 61 (C) on agent readiness against Kronos's 55.2 (C), and leads in 2 of 4 scored categories. Kronos leads on documentation and upkeep.

Other comparisons with EXAONE 4.5 33B or Kronos

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