whatmodel.sh / Phi-1.5 (1.3B)

Phi-1.5 (1.3B)

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

Phi-1.5 (1.3B) is an open-weights language model from Microsoft, released September 2023. Its published size is 1.42B parameters and a 2k-token context window. Licence: mit.

Catalogue identity notes

Phi-1.5 1.3B base model (Li et al. 2023); not instruction-tuned. Not the unreleased phi-1.5-web variants.

31.6±0.7#631 of 719 LLMsfrom 22 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Phi-1.5 (1.3B), out of 828 with a score, then more from Microsoft.

#modelscorewhereRAMreleased
726CodeGemma 2B (v1.0) Google32±1local~3.2GB2024-03
727Qwen-7B (base) Alibaba32±1local~6.6GB2023-08
728Phi-1.5 (1.3B) Microsoft32±1local~2.4GB2023-09
729Falcon-H1 1.5B Instruct TII31±4local~2.4GB2025-05
730Flan-T5 XL Google31±2local~14GB2022-10
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

other tests14 not in a task · 100% of its score
testresultvs the others in its rundifficultycountswhy
ARC Challenge +148.0% ✎▁·▁··▁▁▇▂█▆▃ beats 23/26easy · avg 85%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 41%sharp · at its level · several runs
WinoGrande +172.5% ✎▁····▁··▁▂█▄ beats 25/26easy · avg 89%▇▇▇▇▇ 12%at its level · several runs
BoolQ +174.5% ✎▂▃▂▅▆▂▅▆█▂▂▂ beats 20/26easy · avg 91%▇▇▇▇ 10%at its level · several runs
ARC Easy +173.1% ✎▁▁·▁▁▄▅▄█▅▁▃ beats 23/26easy · avg 88%▇▇▇ 6.4%at its level · several runs
HellaSwag +162.6% ✎▃···▁▇▅█▇▃▁▁ beats 6/26very easy · avg 92%▇▇▇ 6.3%at its level · several runs
OpenBookQA +137.6% ✎█·▁▁▃·▁▃▅▇▃▄ beats 26/26medium · avg 53%▇▇ 4.8%several runs
PIQA +176.3% ✎▁·▁··▁▁▃█▅█▂ beats 12/26easy · avg 88%▇▇ 4.1%blunt · at its level · several runs
MedQA (USMLE, 4 options)31.1% ✎▁▁··▄▁▃··▄▃█ beats 6/17easy · avg 76%▇▇ 4.0%sharp
6 more tests
testresultvs the others in its rundifficultycountswhy
Social IQA +155.4% ✎▁···▁▃█▁▁▁·▃ beats 26/26medium · avg 63%▇ 3.5%blunt · several runs
SciQ93.2% ✎▁·▁·▁·▃▅▃█▄▁ beats 16/26very easy · avg 98%▇ 3.0%maxed out
MedMCQA34.3% ✎▂▂··▄▄▃▂·▄██ beats 6/17medium · avg 68%▇ 2.3%typical
LAMBADA (OpenAI version), last-word accuracy52.7% ✎▁··▃▁▁▁▂▆█▅▃ beats 2/26very easy · avg 89%▇ 1.6%blunt · at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)29.6% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 11/276medium · avg 73%▇ 0.8%at its level · noisy
PubMedQA67.8% ✎▂·▂▆·▄▂▄▄▂█▂ beats 8/17medium · avg 77%▇ 0.4%blunt · at its level

$ 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-1.5 (1.3B) · needs ~0.9 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/phi-1_5-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/phi-1_5-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 Phi-1.5 (1.3B) · needs ~0.9 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/phi-1_5-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 Phi-1.5 (1.3B) · needs ~0.9 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/phi-1_5-GGUF:Q4_K_M

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 Phi-1.5 (1.3B) · needs ~2.8 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/phi-1_5
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/phi-1_5

Other ways to run it

  1. Run it as published · needs ~2.84 GB · from huggingface.co/microsoft (official)
    uv run --with torch --with 'transformers<5' python -c "from transformers import pipeline; print(pipeline('text-generation', model='microsoft/phi-1_5')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/microsoft ↗

$ how the score was worked out · Stability AI — original Stabl… 67%, Textbooks Are All You Need II… 26%, Open Medical-LLM Leaderboard… 7% and 1 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
Stability AI — original StableLM zero-shot evaluation outputs10▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%Apache-2.0
Textbooks Are All You Need II: phi-1.5 technical report — authors' own runs · lab-reported8▇▇▇▇▇▇▇▇ 26%CC BY 4.0
Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)3▇▇ 7%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 31.6

$ 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