whatmodel.sh / Yi-1.5 9B (base)

Yi-1.5 9B (base)

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

Yi-1.5 9B (base) is an open-weights language model from 01.AI, released May 2024. Its published size is 8.83B parameters and a 4k-token context window. Licence: apache-2.0.

Catalogue identity notes

Maker repo 01-ai/Yi-1.5-9B @80d5471: licence tag apache-2.0. 8,829,407,232 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-05: month the maker's Hugging Face repo was created (createdAt 2024-05-11). Pretrained base checkpoint (not an instruct/chat version).

42.1±1.7#498 of 719 LLMsfrom 7 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Yi-1.5 9B (base), out of 828 with a score, then more from 01.AI.

#modelscorewhereRAMreleased
586Tulu 2 DPO 70B Ai242±1local~32GB2023-11
587Mathstral 7B v0.1 Mistral AI42±1local~5.8GB2024-07
588Yi-1.5 9B (base) 01.AI42±2local~6.8GB2024-05
589Claude Instant 1.2 Anthropic42±1comparison only2023-08
590Llama 3 8B Instruct Meta42±0local~6.6GB2024-04
more from 01.AI
308Yi-Lightning 01.AI55±1api price unknown2024-10
373Yi-Large Preview 01.AI52±1comparison only2024-05
396Yi-Large 01.AI51±1comparison only2024-05

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests7 not in a task · 99% of its score
testresultvs the others in its rundifficultycountswhy
MedQA (USMLE, 4 options)55.4% ✎▁▁··▄▁▁··▄▃█ beats 14/17easy · avg 76%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%sharp · at its level
BigCodeBench (Complete)35.5% ✎▂▁▁▄▂▅▇█▆▂▂▂ beats 16/58medium · avg 50%▇▇▇▇▇▇▇▇▇▇▇▇ 30%at its level
MedMCQA53.3% ✎▂▂··▄▄▂▂·▄██ beats 14/17medium · avg 68%▇▇▇▇▇▇▇ 18%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)68.1% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 145/276medium · avg 73%▇▇ 5.8%at its level · noisy
EuroEval HellaSwag (English), test split, 5-shot generative MC, accuracy79.4% ✎▃·▁▁▂▁▂▅█▇▄▁ beats 69/100medium · avg 68%▇▇ 4.4%at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy83.0% ✎▁▁▁▁▁▁▁▂▄█▄▃ beats 83/146easy · avg 83%▇▇ 3.9%at its level · noisy
PubMedQA71.6% ✎▂·▂▆·▄▂▄▄▂█▂ beats 11/17medium · avg 77%▇ 1.9%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 Yi-1.5 9B (base) · needs ~5.3 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/Yi-1.5-9B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/Yi-1.5-9B-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 Yi-1.5 9B (base) · needs ~5.3 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/Yi-1.5-9B-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 Yi-1.5 9B (base) · needs ~5.3 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/Yi-1.5-9B-GGUF: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 Yi-1.5 9B (base) · needs ~5 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Yi-1.5-9B-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Yi-1.5-9B-4bit

Other ways to run it

  1. Run it as published · needs ~17.66 GB · from huggingface.co/01-ai (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='01-ai/Yi-1.5-9B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/01-ai ↗

$ how the score was worked out · Open Medical-LLM Leaderboard… 54%, BigCodeBench paper (Zhuo et a… 30%, EuroEval leaderboards (result… 8% 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
Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 54%Apache-2.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v41▇▇▇▇▇▇▇▇▇ 30%CC BY 4.0
EuroEval leaderboards (results collection), English generative leaderboard2▇▇ 8%MIT
Open Portuguese LLM Leaderboard (archived)1▇▇ 6%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 42.1

$ 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