whatmodel.sh / Stable LM 2 Zephyr 1.6B

Stable LM 2 Zephyr 1.6B

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

Stable LM 2 Zephyr 1.6B is an open-weights language model from Stability AI, released January 2024. Its published size is 1.64B parameters and a 4k-token context window. Licence: other.

Catalogue identity notes

stabilityai/stablelm-2-zephyr-1_6b @2f275b1 (created 2024-01-19, licence other). Independent row: Open PT-LLM (Portuguese) leaderboard average.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 1,644,515,328 parameters.

39.6±6.5#717 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 Stable LM 2 Zephyr 1.6B, out of 1132 with a score, then more from Stability AI.

#modelscorewhereRAMreleased
877LFM2 1.2B Liquid AI40±2local~2.2GB2025-07
878Code Tulu 2 13B Allen Institute for AI40±2local~29GB2023-11
879Stable LM 2 Zephyr 1.6B Stability AI40±7local~2.5GB2024-01
880LLaVA-v1.6-34B LLaVA40±2local~24GB2024-01
881GPT-3.5 text-davinci-002 OpenAI40±5comparison only2022-03
more from Stability AI
661Stable LM 2 12B Chat Stability AI47±6local~8.9GB2024-04
898StableLM Zephyr 3B Stability AI39±7local~3.2GB2023-11
948Stable LM 2 1.6B Chat Stability AI36±7local~2.5GB2024-04

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)55.8% ✎▃▁▁▁▁▁▁▁▃█▅▁ beats 78/276medium · 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 Stable LM 2 Zephyr 1.6B · needs ~1 GB · from huggingface.co/afrideva
    chat in the terminal
    llama cli -hf afrideva/stablelm-2-zephyr-1_6b-GGUF:q4_k_m
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf afrideva/stablelm-2-zephyr-1_6b-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 Stable LM 2 Zephyr 1.6B · needs ~1 GB · from huggingface.co/afrideva

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/afrideva/stablelm-2-zephyr-1_6b-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 Stable LM 2 Zephyr 1.6B · needs ~0.983 GB · from ollama.com
    chat in the terminal
    ollama run stablelm2:zephyr

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 Stable LM 2 Zephyr 1.6B · needs ~1.2 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/stablelm-2-zephyr-1_6b-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/stablelm-2-zephyr-1_6b-4bit

Official weights and documentation: huggingface.co/stabilityai ↗

$ 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= 39.6

$ 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