whatmodel.sh / EXAONE 4.0 1.2B
EXAONE 4.0 1.2B
↗ share
+ contribute
EXAONE 4.0 1.2B is an open-weights language model from LG AI Research, released July 2025. Its published size is 1.28B parameters and a 66k-token context window. Licence: exaone.
$ how it compares
The LLMs ranked either side of EXAONE 4.0 1.2B, out of 828 with a score, then more from LG AI Research.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 476 |  WhiteRabbitNeo-33B-v1 | 47±1 | local | ||
| 477 |  DeepSeek R1 Distill Llama 8B | 47±1 | local | ||
| 478 | EXAONE 4.0 1.2B | 47±2 | local | ||
| 479 |  InternVL2-26B | 47±2 | local | ||
| 480 |  speechless-coder-ds-6.7b | 47±1 | local | ||
| more from LG AI Research | |||||
| 127 | K-EXAONE 2.0 (750B-A37B) | 67±1 | local | ||
| 162 | K-EXAONE (236B-A23B) | 65±1 | local | ||
| 164 | EXAONE 4.5 33B | 65±2 | local | ||
$ what it's good at
agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #269 of 300 · 16% of its score · 3 tests
Beats Magistral Small 1.0 (2506), Llama 4 Scout (109B-A17B), Bielik 11B v2.3 Instruct here, though they rank higher overall. Trails Granite 4.0 H 350M, Qwen3 0.6B, Qwen2.5 1.5B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| τ-bench Retail lab | 28.1% ✎ | ▁····▃·▂▇█▂▆ beats 1/28 | 8.5% |
| τ-bench Airline lab | 20.5% ✎ | ▃▁▁·▅▄▁█▇▁▁▇ beats 0/28 | 5.2% |
| BFCL v3 lab | 52.9% ✎ | ▁▁▁▁▁▃▅█▆▅▄▁ beats 58/170 | 2.5% |
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #283 of 393 * · 6.0% of its score · 1 test
Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, Ministral 3 8B here, though they rank higher overall. Trails Flan-T5 XXL, LFM2 700M, EXAONE 3.5 2.4B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| IFEval (aggregation unspecified) lab | 67.8% ✎ | ▄·▄·▄·▄▄···█ beats 0/6 | 6.0% |
math▁▂▃▅▆▅▄█▄▁▁▁ #251 of 398 * · 34% of its score · 2 tests
Beats GPT-4 Turbo (2024-04-09), Molmo 2 8B, Llama 3.3 70B Instruct here, though they rank higher overall. Trails DeepSeek R1 Distill Qwen 1.5B, Mixtral 8x7B v0.1 (base), Tulu 2 DPO 70B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| AIME 2025 lab | 45.2% ✎ | █·▄▄····▄··█ beats 0/6 | 25% |
| HMMT February 2025 lab | 34.0% ✎ | ▁▁▃▃▁▅▅▃██▁▄ beats 2/31 | 9.1% |
other tests4 not in a task · 42% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GPQA Diamond lab | 52.0% ✎ | █···▄▄···▄·█ beats 0/6 | 22% |
| MMLU-Pro lab | 59.3% ✎ | ▁▁·▁▁▁▃▃▄▅█▁ beats 60/188 | 14% |
| MMLU-Redux lab | 71.5% ✎ | ▁▁▃▁▂▃▄▅▇▅█▄ beats 3/63 | 6.6% |
| Thunder-KoNUBench symbol 0-shot | 26.5% ✎ | █··········█ beats 0/1 | — |
$ where to run it
llama.cpp · recommended
version
- 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 | shWindowsirm https://llama.app/install.ps1 | iex - Run EXAONE 4.0 1.2B · needs ~1.27 GB · from huggingface.co/LGAI-EXAONEchat in the terminal
llama cli -hf LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run EXAONE 4.0 1.2B · needs ~1.27 GB · from huggingface.co/LGAI-EXAONE
- Or download it in the terminal
lms get https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
version
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run EXAONE 4.0 1.2B · needs ~1.27 GB · from huggingface.co/LGAI-EXAONEchat in the terminal
ollama run hf.co/LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF:Q4_K_M
MLX (Mac)
version
- Install MLX (Mac) · Apple silicon Macs only, text only.with uv
uv tool install mlx-lmorpip install mlx-lm - Run EXAONE 4.0 1.2B · needs ~0.7 GB, Mac only · from huggingface.co/lmstudio-communitychat in the terminal
mlx_lm.chat --model lmstudio-community/EXAONE-4.0-1.2B-MLX-4bit - Or start an OpenAI-compatible server at http://localhost:8080/v1
mlx_lm.server --model lmstudio-community/EXAONE-4.0-1.2B-MLX-4bit
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
| source | results | share of the score |
|---|---|---|
 LG AI Research vendor-reported benchmark scores for its own EXAONE models (Hugging Face model cards) · lab-reported | 9 | 99% |
| prior · pull toward the middle | 1% | |
| weighted average | = 46.9 |
not counted (1)
| Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understanding | Thunder-KoNUBench symbol 0-shot [correct] | 26.5% | fewer than three models have this test yet, or this source ran it for this model alone |
$ improve this page
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