whatmodel.sh / EXAONE Deep 7.8B

EXAONE Deep 7.8B

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

EXAONE Deep 7.8B is an open-weights language model from LG AI Research, released March 2025. Its published size is 7.82B parameters and a 33k-token context window. Licence: exaone.

Catalogue identity notes

LGAI-EXAONE/EXAONE-Deep-7.8B @8a12067 (created 2025-03-12, EXAONE AI Model License (non-commercial terms)). EXAONE Deep reasoning model (Mar 2025). Lab rows only: rule-(b) rows from the EXAONE Deep card table (all three sizes), pooled with first-party-lgai-scores GPQA Diamond / AIME 2025 runs of the catalogued EXAONE 4.x models.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 7,818,448,896 parameters.

54.5±1.5#275 of 719 LLMsfrom 5 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of EXAONE Deep 7.8B, out of 828 with a score, then more from LG AI Research.

#modelscorewhereRAMreleased
327OpenThinker 32B Open Thoughts55±1local~21GB2025-02
328Magistral Small 1.1 (2507) Mistral55±2local~16GB2025-07
329EXAONE Deep 7.8B LG AI Research55±2local~6.5GB2025-03
330Qwen2.5-Math 72B Instruct Alibaba55±2local~44GB2024-09
331OpenThinker2 32B Open Thoughts54±1local~21GB2025-04
more from LG AI Research
127K-EXAONE 2.0 (750B-A37B) LG AI Research67±1local~791GB2026-07
162K-EXAONE (236B-A23B) LG AI Research65±1local~152GB2025-12
164EXAONE 4.5 33B LG AI Research65±2local~24GB2026-04

see all LLMs · find the ones that fit your machine

$ what it's good at

coding██·········█ #2 of 3 * · 10% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
LiveCodeBench (version unspecified) lab55.2% ✎▁···▁▁▃▅▅█▄▅ beats 21/37medium · avg 43%▇▇▇▇ 10%at its level · small run
math▁▂▃▅▆▅▄█▄▁▁▁ #193 of 398 · 57% of its score · 3 tests

Beats MiniMax-M2.1, Qwen3 235B-A22B (Apr 2025, hybrid), DeepSeek V3 (Dec '24) here, though they rank higher overall. Trails Phi-4-mini-reasoning 3.8B, DeepSeek R1 Distill Qwen 7B, OpenThinker3 7B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AIME 2025 lab59.6% ✎█·▄▄····▄··█ beats 2/6medium · avg 53%▇▇▇▇▇▇▇▇▇▇ 26%sharp · at its level
AIME 2024 lab70.0% ✎▁▁▁▂▁▃▁▅███▃ beats 36/85medium · avg 54%▇▇▇▇▇▇▇▇ 20%sharp · at its level · small run
MATH-500 lab94.8% ✎▁▃▂▃▅▇▅▇█▅▂▁ beats 53/84very easy · avg 91%▇▇▇▇▇ 12%maxed out · small run
other tests1 not in a task · 31% of its score
testresultvs the others in its rundifficultycountswhy
GPQA Diamond lab62.6% ✎█···▄▄···▄·█ beats 2/6hard · avg 51%▇▇▇▇▇▇▇▇▇▇▇▇ 31%sharp · at its level

$ where to run it

llama.cpp · recommended

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run EXAONE Deep 7.8B · needs ~4.77 GB · from huggingface.co/LGAI-EXAONE
    chat in the terminal
    llama cli -hf LGAI-EXAONE/EXAONE-Deep-7.8B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf LGAI-EXAONE/EXAONE-Deep-7.8B-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run EXAONE Deep 7.8B · needs ~4.77 GB · from huggingface.co/LGAI-EXAONE

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/LGAI-EXAONE/EXAONE-Deep-7.8B-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run EXAONE Deep 7.8B · needs ~4.8 GB · from ollama.com
    chat in the terminal
    ollama run exaone-deep:7.8b

MLX (Mac)

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run EXAONE Deep 7.8B · needs ~8.3 GB, Mac only · from huggingface.co/sinbal
    chat in the terminal
    mlx_lm.chat --model sinbal/EXAONE-Deep-7.8B-MLX-8bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model sinbal/EXAONE-Deep-7.8B-MLX-8bit

Weights and documentation: huggingface.co/LGAI-EXAONE ↗

$ how the score was worked out · LG AI Research vendor-reporte… 99%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LG AI Research vendor-reported benchmark scores for its own EXAONE models (Hugging Face model cards) · lab-reported5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Factual vendor-reported score (not licensed content)
prior · pull toward the middle▇ 1%
weighted average= 54.5

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json