whatmodel.sh / Phi-3-mini-4k-instruct (Apr 2024)

Phi-3-mini-4k-instruct (Apr 2024)

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

Phi-3-mini-4k-instruct (Apr 2024) is an open-weights language model from Microsoft, released April 2024. Its published size is 3.82B parameters. Licence: mit.

Catalogue identity notes

Comparison-only. Arena entry 'phi-3-mini-4k-instruct' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'phi-3-mini-4k-instruct' as 'Phi-3-Mini-4k-Instruct' (Microsoft, MIT), linking https://huggingface.co/microsoft/Phi-3-mini-4k-instruct. Maker repo microsoft/Phi-3-mini-4k-instruct @f39ac1d: licence tag mit. 3,821,079,552 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-04: month the maker's Hugging Face repo was created (createdAt 2024-04-22). Original April 2024 release. The same HF repo now holds the 'June 2024 Update' (a separate Arena entry, phi-3-mini-4k-instruct-june-2024), so no run option is given for this checkpoint.

38.1±1.6#562 of 719 LLMsfrom 5 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of Phi-3-mini-4k-instruct (Apr 2024), out of 828 with a score, then more from Microsoft.

#modelscorewhereRAMreleased
652Code Llama 13B Python Meta38±1local~9.8GB2023-08
653Tulu 2 13B Allen Institute for AI38±2local~9.8GB2023-11
654Phi-3-mini-4k-instruct (Apr 2024) Microsoft38±2local~4GB2024-04
655Apertus 8B Instruct (2509) Swiss AI38±4local~6.3GB2025-08
656LLaMA 65B Meta38±1comparison only2023-02
more from Microsoft
252Phi-4-reasoning-plus 14B Microsoft59±1local~10GB2025-04
261Phi-4-reasoning 14B Microsoft58±1api $0.22/M +local~10GB2025-04
365Phi-4 14B Microsoft53±1api $0.087/M +local~10GB2024-12

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #365 of 393 * · 48% of its score · 2 tests

Beats Gemma 4 E2B, Code Llama 70B Instruct, Phi-2 (2.7B) 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
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1068.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 32/95avg 1201▇▇▇▇▇▇▇▇▇▇ 24%blunt
LMArena (text)1128.1 ✎▁▁▁▃▃▃▃▆▆▇█▃ beats 26/379avg 1268▇▇▇▇▇▇▇▇▇ 24%blunt
other tests3 not in a task · 51% of its score
testresultvs the others in its rundifficultycountswhy
MMLU-Pro41.5% ✎▃▂▅█▃·█▃▅··▂ beats 7/23medium · avg 57%▇▇▇▇▇▇▇▇▇▇▇▇▇ 33%at its level
Polish EQ-Bench v2 (SpeakLeash)28.1% ✎▁··▁▁▃▂▆▅▆█▆ beats 7/70medium · avg 64%▇▇▇▇▇ 13%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)66.4% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 125/276medium · avg 73%▇▇ 4.9%at its level · 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 Phi-3-mini-4k-instruct (Apr 2024) · needs ~2.39 GB · from huggingface.co/microsoft (official)
    chat in the terminal
    llama cli -hf microsoft/Phi-3-mini-4k-instruct-gguf
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf microsoft/Phi-3-mini-4k-instruct-gguf

LM Studio

version

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

    download it (macOS / Windows / Linux) ↗

  2. Run Phi-3-mini-4k-instruct (Apr 2024) · needs ~2.39 GB · from huggingface.co/microsoft (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf -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 Phi-3-mini-4k-instruct (Apr 2024) · needs ~2.39 GB · from huggingface.co/microsoft (official)
    chat in the terminal
    ollama run hf.co/microsoft/Phi-3-mini-4k-instruct-gguf

Official weights and documentation: huggingface.co/microsoft ↗

$ how the score was worked out · MMLU-Pro author-released eval… 33%, Polyrating: A Cost-Effective… 24%, LMArena leaderboard dataset 24% 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
MMLU-Pro author-released evaluation runs1▇▇▇▇▇▇▇▇▇▇ 33%Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇▇▇▇▇▇ 24%CC-BY-4.0
LMArena leaderboard dataset1▇▇▇▇▇▇▇ 24%CC BY 4.0
SpeakLeash Polish EQ-Bench leaderboard1▇▇▇▇ 13%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 5%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 38.1

$ 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