whatmodel.sh / Zephyr ORPO 141B-A35B v0.1

Zephyr ORPO 141B-A35B v0.1

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

Zephyr ORPO 141B-A35B v0.1 is an open-weights language model from Hugging Face, released April 2024. Its published size is 141B parameters (39B active per token) and a 66k-token context window. Licence: apache-2.0.

Catalogue identity notes

Arena entry 'zephyr-orpo-141b-A35b-v0.1' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'zephyr-orpo-141b-A35b-v0.1' as 'Zephyr-ORPO-141b-A35b-v0.1' (HuggingFace, Apache 2.0), linking https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1. Maker repo HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 @a3be084: licence tag apache-2.0. Parameters: card: 'A Mixture of Experts (MoE) model with 141B total parameters and 39B active parameters' (the card notes the A35b in the repo name was a miscalculation). Released 2024-04: month the maker's Hugging Face repo was created (createdAt 2024-04-10).

44.9±1.9#444 of 719 LLMsfrom 4 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of Zephyr ORPO 141B-A35B v0.1, out of 828 with a score, then more from Hugging Face.

#modelscorewhereRAMreleased
530GPT-4o Audio Preview (2024-10-01) OpenAI45±3comparison only2024-10
531Claude 2.1 Anthropic45±1comparison only2023-11
532Zephyr ORPO 141B-A35B v0.1 Hugging Face45±2local~56GB2024-04
533Phi-3-medium-4k-instruct Microsoft45±1local~9.8GB2024-05
534Qwen2-Math 1.5B Instruct Alibaba45±2local~2.4GB2024-08
more from Hugging Face
451StarChat2 15B v0.1 Hugging Face48±1local~12GB2024-03
577SmolLM3 3B Hugging Face43±1local~3.3GB2025-07
678Zephyr 7B alpha Hugging Face36±1local~6.1GB2023-10

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #296 of 393 · 74% of its score · 3 tests

Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, OpenThinker3 7B here, though they rank higher overall. Trails LFM2 350M, Flan-T5 XXL, LFM2 700M here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1143.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 63/95avg 1201▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%blunt
LMArena (text)1213.0 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 75/379avg 1268▇▇▇▇▇▇▇▇▇▇▇▇▇ 33%blunt
IFEval (aggregation unspecified) lab65.1% ✎▁▁▃▁▃▄▄▆█▃▂▁ beats 27/141easy · avg 73%▇▇▇ 6.7%at its level · small run
other tests1 not in a task · 25% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard lab59.0% ✎▁▁▁▁▂▄▅▅█▃▄▁ beats 63/129medium · avg 67%▇▇▇▇▇▇▇▇▇▇ 25%sharp · at its level · small run

$ 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 Zephyr ORPO 141B-A35B v0.1 · needs ~85.6 GB · from huggingface.co/MaziyarPanahi
    chat in the terminal
    llama cli -hf MaziyarPanahi/zephyr-orpo-141b-A35b-v0.1-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf MaziyarPanahi/zephyr-orpo-141b-A35b-v0.1-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 Zephyr ORPO 141B-A35B v0.1 · needs ~85.6 GB · from huggingface.co/MaziyarPanahi

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/MaziyarPanahi/zephyr-orpo-141b-A35b-v0.1-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 Zephyr ORPO 141B-A35B v0.1 · needs ~85.1 GB · from ollama.com
    chat in the terminal
    ollama run zephyr:141b-v0.1-q4_0

Weights and documentation: huggingface.co/HuggingFaceH4 ↗

$ how the score was worked out · Polyrating: A Cost-Effective… 34%, LMArena leaderboard dataset 33%, HuggingFaceH4 zephyr-orpo-141… 31%

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
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇▇▇▇▇▇▇▇▇ 34%CC-BY-4.0
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇ 33%CC BY 4.0
HuggingFaceH4 zephyr-orpo-141b-A35b-v0.1 model card · lab-reported2▇▇▇▇▇▇▇▇▇ 31%Apache-2.0
prior · pull toward the middle▇ 2%
weighted average= 44.9

$ 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