whatmodel.sh / SmolLM2 135M Instruct

SmolLM2 135M Instruct

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

SmolLM2 135M Instruct is an open-weights language model from Hugging Face, released October 2024. Its published size is 0.135B parameters and a 8k-token context window. Licence: apache-2.0.

Catalogue identity notes

HuggingFaceTB/SmolLM2-135M-Instruct @12fd25f (created 2024-10-31, licence apache-2.0). Hugging Face SmolLM2 135M instruct model, sibling of the catalogued smollm2-1-7b. Independent EuroEval row only (its card compares only against the uncatalogued SmolLM-135M-Instruct).

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 134,515,008 parameters (HuggingFaceTB/SmolLM2-135M-Instruct @12fd25f).

20.6±8.6#914 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of SmolLM2 135M Instruct, out of 1132 with a score, then more from Hugging Face.

#modelscorewhereRAMreleased
1092Phi-1 (1.3B) Microsoft21±4local~2.4GB2023-09
1093Qwen1.5 0.5B Chat Alibaba21±3local~1.8GB2024-01
1094SmolLM2 135M Instruct Hugging Face21±9local~1.6GB2024-10
1095ChatGLM-6B Zhipu AI (THUDM)20±2local~16GB2023-03
1096Pythia 2.8B (deduped) EleutherAI20±1local~3.4GB2023-02
more from Hugging Face
629StarChat2 15B v0.1 Hugging Face48±1local~12GB2024-03
742Zephyr ORPO 141B-A35B v0.1 Hugging Face45±2local~56GB2024-04
808SmolLM3 3B Hugging Face43±1local~3.3GB2025-07

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 67% of its score
testresultvs the others in its rundifficultycountswhy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy24.8% ✎▃▁▁▁▁▁▁▂▄█▄▃ beats 1/146easy · avg 83%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%noisy

$ where to run it

llama.cpp · recommended

version

  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 SmolLM2 135M Instruct · needs ~0.1 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/SmolLM2-135M-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/SmolLM2-135M-Instruct-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 SmolLM2 135M Instruct · needs ~0.1 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/SmolLM2-135M-Instruct-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 SmolLM2 135M Instruct · needs ~0.271 GB · from ollama.com
    chat in the terminal
    ollama run smollm2:135m

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run SmolLM2 135M Instruct · needs ~0.1 GB, Mac only · from huggingface.co/Irfanuruchi
    chat in the terminal
    mlx_lm.chat --model Irfanuruchi/SmolLM2-135M-Instruct-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model Irfanuruchi/SmolLM2-135M-Instruct-MLX-4bit

Weights and documentation: huggingface.co/HuggingFaceTB ↗

$ how the score was worked out · EuroEval leaderboards (result… 67%

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
EuroEval leaderboards (results collection), English generative leaderboard1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%MIT
prior · pull toward the middle▇▇▇▇▇▇▇▇▇▇ 33%
weighted average= 20.6

$ 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