whatmodel.sh / Zephyr 7B alpha

Zephyr 7B alpha

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

Zephyr 7B alpha is an open-weights language model from Hugging Face, released October 2023. Its published size is 7.24B parameters. Licence: mit.

Catalogue identity notes

Arena entry 'zephyr-7b-alpha' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'zephyr-7b-alpha' as 'Zephyr-7B-alpha' (HuggingFace, MIT), linking https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha. Maker repo HuggingFaceH4/zephyr-7b-alpha @014792b: licence tag mit. 7,241,732,096 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-10: month the maker's Hugging Face repo was created (createdAt 2023-10-09).

36.3±1.1#585 of 719 LLMsfrom 10 benchmark results across 6 sources

$ how it compares

The LLMs ranked either side of Zephyr 7B alpha, out of 828 with a score, then more from Hugging Face.

#modelscorewhereRAMreleased
676Yi 1.5 6B Chat 01.AI37±2local~5.1GB2024-05
677Falcon3 3B Instruct TII37±3local~3.4GB2024-12
678Zephyr 7B alpha Hugging Face36±1local~6.1GB2023-10
679Vicuna 13B v1.5 LMSYS36±2local~9.8GB2023-08
680Granite 3.1 2B Instruct IBM36±1local~3.1GB2024-12
more from Hugging Face
451StarChat2 15B v0.1 Hugging Face48±1local~12GB2024-03
532Zephyr ORPO 141B-A35B v0.1 Hugging Face45±2local~56GB2024-04
577SmolLM3 3B Hugging Face43±1local~3.3GB2025-07

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #366 of 393 · 48% of its score · 4 tests

Beats Gemma 4 E2B, Code Llama 70B Instruct, Phi-2 (2.7B) here, though they rank higher overall. Trails Gemma 3 270M IT, SmolLM2 360M Instruct, Granite 4.0 350M here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled10.3% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 22/122medium · avg 39%▇▇▇▇▇▇▇▇ 21%typical
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1051.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 26/95avg 1201▇▇▇▇ 11%blunt
LMArena (text)1126.9 ✎▁▁▁▃▃▃▃▆▆▇█▃ beats 24/379avg 1268▇▇▇▇ 11%blunt
AlpacaEval 1.0 win rate (vs text-davinci-003, GPT-4 judge)85.8% ✎▂▂·▆·▇▃▆█▆▄▂ beats 23/45very easy · avg 96%▇▇ 4.6%sharp · noisy
other tests6 not in a task · 52% of its score
testresultvs the others in its rundifficultycountswhy
LiveBench 2024-07-2618.6% ✎▁▁▁▂▂▃▂█▆▃▅▃ beats 13/61medium · avg 41%▇▇▇▇▇▇▇▇▇▇▇ 28%typical
Natural Questions (closed book)26.2% ✎▁·▁·▁▂▁▂·▅▂█ beats 21/28medium · avg 58%▇▇▇▇▇▇▇ 18%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)66.2% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 122/276medium · avg 73%▇ 2.2%at its level · noisy
TriviaQA65.9% ✎▁··▁█▃▃▁▄▅▄█ beats 25/28easy · avg 79%▇ 2.0%at its level · noisy
HaluEval QA hallucination detection (accuracy)62.4% ✎█▁▁·▁▁·▁▁▁▃▁ beats 25/27medium · avg 70%▇ 1.3%sharp · noisy
TruthfulQA MC256.0% ✎▅▃█▆▁▂▅···▁▁ beats 29/31medium · avg 64%▇ 0.9%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 Zephyr 7B alpha · needs ~4.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/zephyr-7b-alpha-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/zephyr-7b-alpha-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 7B alpha · needs ~4.4 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/zephyr-7b-alpha-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 7B alpha · needs ~4.84 GB · from ollama.com
    chat in the terminal
    ollama run zephyr:7b-alpha-q4_K_M

Weights and documentation: huggingface.co/HuggingFaceH4 ↗

$ how the score was worked out · LiveBench model judgments (HF… 28%, AlpacaEval 1.0 and 2.0 leader… 26%, Hallucinations Leaderboard re… 22% and 3 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
LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets1▇▇▇▇▇▇▇▇ 28%Apache-2.0 (stated in the LiveBench datasheet)
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)2▇▇▇▇▇▇▇▇ 26%Apache-2.0
Hallucinations Leaderboard results (HF dataset hallucinations-leaderboard/results)4▇▇▇▇▇▇▇ 22%Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇▇ 11%CC-BY-4.0
LMArena leaderboard dataset1▇▇▇ 11%CC BY 4.0
Open Portuguese LLM Leaderboard (archived)1▇ 2%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 36.3

$ 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