whatmodel.sh / Solar Pro Preview (22B)

Solar Pro Preview (22B)

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

Solar Pro Preview (22B) is an open-weights language model from Upstage, released September 2024. Its published size is 22.14B parameters and a 4k-token context window. Licence: mit.

Catalogue identity notes

upstage/solar-pro-preview-instruct @dd4bcf7 (created 2024-09-09, licence mit). Independent row: Open PT-LLM (Portuguese) leaderboard average.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 22,140,032,000 parameters.

50.5±6.5#426 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Solar Pro Preview (22B), out of 1132 with a score, then more from Upstage.

#modelscorewhereRAMreleased
554Reka Flash (2024-09-04) Reka AI51±3comparison only2024-09
555Bielik 11B v2.0 Instruct SpeakLeash51±3local~8.5GB2024-08
556Solar Pro Preview (22B) Upstage51±7local~15GB2024-09
557OpenThinker3 7B Open Thoughts50±1local~6GB2025-05
558CodeQwen1.5 7B Chat Alibaba50±1local~6.4GB2024-04
more from Upstage
84Solar Open 2 (250B-A15B) Upstage72±1local~527GB2026-07
200Solar Pro 4 Upstage65±2api $0.53/M2026-08
294Solar Open 100B (102B-A12B) Upstage60±1local~41GB2025-12

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 81% of its score
testresultvs the others in its rundifficultycountswhy
Open PT-LLM Leaderboard average (9 Portuguese tasks)73.7% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 209/276medium · avg 73%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%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 Solar Pro Preview (22B) · needs ~13.3 GB · from huggingface.co/MaziyarPanahi
    chat in the terminal
    llama cli -hf MaziyarPanahi/solar-pro-preview-instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf MaziyarPanahi/solar-pro-preview-instruct-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 Solar Pro Preview (22B) · needs ~13.3 GB · from huggingface.co/MaziyarPanahi

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/MaziyarPanahi/solar-pro-preview-instruct-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Solar Pro Preview (22B) · needs ~13 GB · from ollama.com
    chat in the terminal
    ollama run solar-pro:22b

Official weights and documentation: huggingface.co/upstage ↗

$ how the score was worked out · Open Portuguese LLM Leaderboa… 81%

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 Portuguese LLM Leaderboard (archived)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%Apache-2.0
prior · pull toward the middle▇▇▇▇▇▇ 19%
weighted average= 50.5

$ 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