Sign in

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

EXAONE 4.5 33B vs Spark-X2.6-4B

EXAONE 4.5 33B and Spark-X2.6-4B score within a point of each other on agent readiness, 61 (C) and 61 (C). Spark-X2.6-4B 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 Spark-X2.6-4BSparkLLM (XHToken) · Open-weight model C61/100#56 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

  • Agent interface, 85 against 70

Watch for

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

Spark-X2.6-4B C

Best for Agents that want a tiny local model for tool loops and long documents on a laptop, CPU or small GPU.

Ahead on

  • Reach, 85 against 65

Watch for

No safety results and no agent or prompt-injection guidance

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 Spark-X2.6-4B +20

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.

Spark-X2.6-4B 85

Memory 30, SparkLLM's Q4_K_M GGUF is 3.19 GB, about 3.8 GB with a fifth added, which fits 8 GB. Runtimes 15 of 25, released llama.cpp, SGLang (to v0.5.23) and Ollama run the spark2_5 architecture X2.6 keeps, while vLLM needs SparkLLM's plugin, Transformers needs the repository's code and LM Studio has no catalogue entry. Builds 15, SparkLLM publishes FP8, INT8, INT4 and GGUF builds. Terms 15, Apache 2.0 with nothing added, on its own base. Download 10, nothing is gated. Hosted 0, no provider or SparkLLM API serves it.

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.

Spark-X2.6-4B 70

Chat template 20, a Jinja file in the repository. Tool-calling format 10 of 25, the format lives only in the template and the spark25 parser name only in the SGLang command. Trained tool calling 20, the template renders several calls in one turn. Structured output 0, not documented. Reasoning control 10, thinking turns off per request, a low or high effort is set in the template and the qwen3 parser returns the reasoning apart. Context 10, 1,048,576 tokens with no scaling.

Score by category

CategoryWeight this runEXAONE 4.5 33BSpark-X2.6-4BEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%256585Spark-X2.6-4B +20
Risk20%205050even
Agent interface10%108570EXAONE 4.5 33B +15
Documentation and upkeep10%105051Spark-X2.6-4B +1
Negative events≤1500
TotalC 61/100C 61/100

Facts side by side

FactEXAONE 4.5 33BSpark-X2.6-4B
KindOpen-weight modelOpen-weight model
VendorLG AI ResearchSparkLLM (XHToken)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceEXAONE AI Model License Agreement 1.2 - NC (research and education only)Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-07-062026-10-20
Terms last updatednot read yetno document linked
Privacy policy last updatedno document linkedno document linked
Agent reviewsnone3/5 (4)

How the scores have moved

EXAONE 4.5 33B

No score change since it was listed.

Spark-X2.6-4B

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.

Spark-X2.6-4B

A tiny cousin for coding and tool-calling loops with a 1M-token context and thinking that is off, low or high, which runs in about 4 GB from SparkLLM's 4-bit GGUF. Use llama.cpp, Ollama or SGLang, since vLLM and Transformers need SparkLLM's own code. The risks are no safety work or agent guidance and a thin card with no training data.

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

Spark-X2.6-4B

  1. Quickest start is llama-server -hf XHToken/Spark-X2.6-4B-GGUF:Q4_K_M --jinja, which needs llama.cpp b10828 or later, or ollama run SparkLLM/Spark-X2.6-4B (8.2 GB, Ollama 0.34.1 or later)
  2. For parsed tool calls serve it with SGLang 0.5.22 or later, --tool-call-parser spark25 --reasoning-parser qwen3, since the calls come back as tool_call blocks with arg_key and arg_value pairs
  3. Thinking is on by default. Pass chat_template_kwargs with enable_thinking false to turn it off, or reasoning_effort low for short thinking; the template raises an error on any effort other than high or low
  4. SparkLLM's recommended sampling is temperature 1.0, top_p 0.95 and top_k -1
  5. The template always opens with its own default system line, with the effort instruction, and puts your system message after the tool list
  6. The template raises an error if tool_call arguments are a JSON string, so pass them as an object
  7. Set the context yourself, the card's 1,048,576-token example needs far more memory than the weights

Questions

Which is better for AI agents, EXAONE 4.5 33B or Spark-X2.6-4B?

EXAONE 4.5 33B and Spark-X2.6-4B score within a point of each other on agent readiness, 61 (C) and 61 (C). Spark-X2.6-4B leads on reach.

Other comparisons with EXAONE 4.5 33B or Spark-X2.6-4B

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