whatmodel.sh / Yi 34B 200K (base)

Yi 34B 200K (base)

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

Yi 34B 200K (base) is an open-weights language model from 01.AI, released November 2023. Its published size is 34.39B parameters and a 200k-token context window. Licence: apache-2.0.

Catalogue identity notes

Maker repo 01-ai/Yi-34B-200K @e0ae1af: licence tag apache-2.0. 34,388,921,088 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-11: month the maker's Hugging Face repo was created (createdAt 2023-11-06). Pretrained base checkpoint (not an instruct/chat version).

49.9±4.5#344 of 719 LLMsfrom 3 benchmark results across 2 sources

$ how it compares

The LLMs ranked either side of Yi 34B 200K (base), out of 828 with a score, then more from 01.AI.

#modelscorewhereRAMreleased
412Llama 3.2 90B Vision Instruct Meta50±1local~58GB2024-09
413DeepSeek-Coder 33B Instruct DeepSeek50±1local~21GB2023-11
414Yi 34B 200K (base) 01.AI50±5local~23GB2023-11
415Gemma 2 27B IT Google50±1local~18GB2024-06
416Bielik 11B v2.3 Instruct SpeakLeash50±2local~8.6GB2024-08
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 tests3 not in a task · 91% of its score
testresultvs the others in its rundifficultycountswhy
Open PT-LLM Leaderboard average (9 Portuguese tasks)68.8% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 156/276medium · avg 73%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 38%at its level · noisy
RULER 64k83.2% ✎▁▁·▁·▂▃▄█▂·▁ beats 9/22easy · avg 83%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 38%typical
RULER 128k77.3% ✎▄··▂▄▂▆██▄▄▂ beats 16/21easy · avg 68%▇▇▇▇▇▇ 15%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 34B 200K (base) · needs ~20.7 GB · from huggingface.co/TheBloke
    chat in the terminal
    llama cli -hf TheBloke/Yi-34B-200K-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf TheBloke/Yi-34B-200K-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 34B 200K (base) · needs ~20.7 GB · from huggingface.co/TheBloke

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/TheBloke/Yi-34B-200K-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 34B 200K (base) · needs ~20.7 GB · from huggingface.co/TheBloke
    chat in the terminal
    ollama run hf.co/TheBloke/Yi-34B-200K-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 Yi 34B 200K (base) · needs ~36.5 GB, Mac only · from huggingface.co/Fmuaddib
    chat in the terminal
    mlx_lm.chat --model Fmuaddib/Yi-34B-200K-mlx-8Bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model Fmuaddib/Yi-34B-200K-mlx-8Bit

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-34B-200K', 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 · NVIDIA RULER repository READM… 53%, Open Portuguese LLM Leaderboa… 38%

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
NVIDIA RULER repository README results table2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 53%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇▇▇▇▇▇▇▇▇▇▇▇ 38%Apache-2.0
prior · pull toward the middle▇▇▇ 9%
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