whatmodel.sh / Yi-1.5 34B Chat 16K

Yi-1.5 34B Chat 16K

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

Yi-1.5 34B Chat 16K is an open-weights language model from 01.AI, released May 2024. Its published size is 34.39B parameters and a 16k-token context window. Licence: apache-2.0.

Catalogue identity notes

Maker repo 01-ai/Yi-1.5-34B-Chat-16K @ff74452: licence tag apache-2.0. 34,388,917,248 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-05: month the maker's Hugging Face repo was created (createdAt 2024-05-15).

49.9±3.8#445 of 949 LLMsfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Yi-1.5 34B Chat 16K, out of 1132 with a score, then more from 01.AI.

#modelscorewhereRAMreleased
574DeepSeek-Coder 33B Instruct DeepSeek50±1local~21GB2023-11
575Yi 34B 200K (base) 01.AI50±5local~23GB2023-11
576Yi-1.5 34B Chat 16K 01.AI50±4local~22GB2024-05
577Llama-3-Instruct-8B-SPPO-Iter3 UCLA AGI (SPPO)50±2local~6.6GB2024-06
578Gemma 2 27B IT Google50±1local~18GB2024-06
more from 01.AI
404Yi-Lightning 01.AI55±1api price unknown2024-10
506Yi-Large Preview 01.AI52±1comparison only2024-05
547Yi-Large 01.AI51±1comparison only2024-05

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests2 not in a task · 93% of its score
testresultvs the others in its rundifficultycountswhy
BRIDGE clinical text, zero-shot average (87 tasks)32.1% ✎▁▁▁▁▁▂▂▃▄▆█▃ beats 36/97hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 65%blunt · at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)71.9% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 189/276medium · avg 73%▇▇▇▇▇▇▇▇▇▇▇ 28%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 Yi-1.5 34B Chat 16K · needs ~20.7 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/Yi-1.5-34B-Chat-16K-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/Yi-1.5-34B-Chat-16K-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 34B Chat 16K · needs ~20.7 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/Yi-1.5-34B-Chat-16K-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 34B Chat 16K · needs ~20.7 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/Yi-1.5-34B-Chat-16K-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 34B Chat 16K · needs ~19.3 GB, Mac only · from huggingface.co/Fmuaddib
    chat in the terminal
    mlx_lm.chat --model Fmuaddib/Yi-1.5-34B-Chat-16K-mlx-4Bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model Fmuaddib/Yi-1.5-34B-Chat-16K-mlx-4Bit

Other ways to run it

  1. Run it as published · needs ~68.78 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-1.5-34B-Chat-16K', 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 · BRIDGE Medical Leaderboard (H… 65%, Open Portuguese LLM Leaderboa… 28%

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
BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 65%MIT
Open Portuguese LLM Leaderboard (archived)1▇▇▇▇▇▇▇▇▇ 28%Apache-2.0
prior · pull toward the middle▇▇ 7%
weighted average= 49.9

$ 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