whatmodel.sh / SmolLM2 1.7B Instruct

SmolLM2 1.7B Instruct

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

SmolLM2 1.7B Instruct is an open-weights language model from Hugging Face, released October 2024. Its published size is 1.71B parameters and a 8k-token context window. Licence: apache-2.0.

Catalogue identity notes

Arena entry 'smollm2-1.7b-instruct' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'smollm2-1.7b-instruct' as 'SmolLM2-1.7B-Instruct' (HuggingFace, Apache 2.0), linking https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct. Maker repo HuggingFaceTB/SmolLM2-1.7B-Instruct @31b70e2: licence tag apache-2.0. 1,711,376,384 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-10: month the maker's Hugging Face repo was created (createdAt 2024-10-31).

30.3±1.1#641 of 719 LLMsfrom 18 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of SmolLM2 1.7B Instruct, out of 828 with a score, then more from Hugging Face.

#modelscorewhereRAMreleased
736OPT-66B Meta31±1local~141GB2022-05
737LFM2 350M Liquid AI30±2local~1.7GB2025-07
738SmolLM2 1.7B Instruct Hugging Face30±1local~2.6GB2024-10
739Llama 3.2 1B Instruct Meta30±1api $0.020/M +local~2.2GB2024-09
740Falcon 7B (base) TII30±1local~5.9GB2023-04
more from Hugging Face
451StarChat2 15B v0.1 Hugging Face48±1local~12GB2024-03
532Zephyr ORPO 141B-A35B v0.1 Hugging Face45±2local~56GB2024-04
577SmolLM3 3B Hugging Face43±1local~3.3GB2025-07

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #405 of 458 * · 7.1% of its score · 1 test

Beats DeepSeek R1 Distill Qwen 7B, Qwen3.5 2B, DeepSeek R1 Distill Llama 8B here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
HumanEval lab28.1% ✎▁▁▁▁▁▃▅▅█▃▂▁ beats 28/190easy · avg 80%▇▇▇ 7.1%sharp · at its level · small run
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #373 of 393 · 19% of its score · 4 tests

Beats Phi-2 (2.7B), Qwen2.5 1.5B Instruct, Nous-Hermes-13b here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Granite 4.0 350M here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1114.6 ✎▁▁▁▃▃▃▃▆▆▇█▃ beats 19/379avg 1268▇▇▇▇ 11%blunt
IFEval prompt-level loose51.6% ✎▁▃▁▃▁▄▁▁█▃▃▁ beats 1/22easy · avg 80%▇ 3.1%at its level
AlpacaEval 2 length-controlled5.8% ✎▃▃·▁▁█▇▅·▁·▁ beats 0/22medium · avg 42%▇ 2.3%too hard for it
IFEval (aggregation unspecified) lab56.7% ✎▁▁▃▃▂▄▄▆█▃▂▁ beats 20/141easy · avg 77%▇ 2.1%at its level · small run
math▁▂▃▅▆▅▄█▄▁▁▁ #369 of 398 · 28% of its score · 2 tests

Beats Yi 34B Chat, Command R (03-2024), Molmo 7B-D (0924) here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
GSM8K +145.3% ✎▂▃··▃▂▅█▆▃▂▃ beats 1/22very easy · avg 88%▇▇▇▇▇▇▇▇ 21%sharp · at its level · several runs
MATH (subset unspecified) +120.3% ✎▃▃█▂▂▆·····▁ beats 0/22medium · avg 62%▇▇▇ 7.9%small run · several runs
other tests8 not in a task · 45% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard +139.8% ✎▁▄·▁▁·▅█·▄▄▁ beats 2/22easy · avg 75%▇▇▇▇▇▇ 15%sharp · several runs
MMLU34.3% ✎▃▂·▁·▁▁█·▃▃▅ beats 0/22easy · avg 77%▇▇▇▇▇ 12%typical
CPTUB average (SpeakLeash, 0-5 judge scale)29.9% ✎▃▂▂▂▃█▃▆▅▄▂▃ beats 1/95easy · avg 66%▇▇▇ 7.5%at its level
HellaSwag lab66.1% ✎▁▁▁▁▂▂▃▇█▆▅▃ beats 33/85easy · avg 86%▇ 3.4%at its level · small run
TruthfulQA MC245.3% ✎▃▃▂·▃▃·▅█▂▅▂ beats 2/21medium · avg 63%▇ 2.4%blunt · at its level
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy50.2% ✎▁▁▁▁▁▁▃▂▄█▄▃ beats 19/146easy · avg 83%▇ 1.6%at its level · noisy
PIQA lab74.4% ✎▁▁▁▃▃▄▇█▄▃▁▁ beats 33/83easy · avg 86%▇ 1.6%blunt · at its level · small run
PopQA16.4% ✎▁▁▁▃▃▃▁█▁▃·▄ beats 4/21hard · avg 32%▇ 1.6%blunt

$ 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 SmolLM2 1.7B Instruct · needs ~1.1 GB · from huggingface.co/HuggingFaceTB
    chat in the terminal
    llama cli -hf HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF:q4_k_m
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf HuggingFaceTB/SmolLM2-1.7B-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 1.7B Instruct · needs ~1.1 GB · from huggingface.co/HuggingFaceTB

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF@q4_k_m -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run SmolLM2 1.7B Instruct · needs ~1.53 GB · from ollama.com
    chat in the terminal
    ollama run smollm2:1.7b-instruct-q4_K_M

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 1.7B Instruct · needs ~1 GB, Mac only · from huggingface.co/Irfanuruchi
    chat in the terminal
    mlx_lm.chat --model Irfanuruchi/SmolLM2-1.7B-Instruct-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model Irfanuruchi/SmolLM2-1.7B-Instruct-MLX-4bit

Weights and documentation: huggingface.co/HuggingFaceTB ↗

$ how the score was worked out · 2 OLMo 2 Furious (Team OLMo,… 45%, SmolLM2 paper (Hugging Face)… 34%, LMArena leaderboard dataset 11% and 2 more

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
2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct models8▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%CC BY 4.0
SmolLM2 paper (Hugging Face) — authors' own instruct-model evaluations · lab-reported7▇▇▇▇▇▇▇▇▇▇ 34%CC BY 4.0
LMArena leaderboard dataset1▇▇▇ 11%CC BY 4.0
SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)1▇▇ 8%MIT
EuroEval leaderboards (results collection), English generative leaderboard1▇ 2%MIT
prior · pull toward the middle▇ 1%
weighted average= 30.3

$ 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