whatmodel.sh / Starling-LM 7B beta

Starling-LM 7B beta

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

Starling-LM 7B beta is an open-weights language model from Nexusflow, released March 2024. Its published size is 7.24B parameters and a 8k-token context window. Licence: apache-2.0.

Catalogue identity notes

Arena entry 'starling-lm-7b-beta' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'starling-lm-7b-beta' as 'Starling-LM-7B-beta' (Nexusflow, Apache-2.0), linking https://huggingface.co/Nexusflow/Starling-LM-7B-beta. Maker repo Nexusflow/Starling-LM-7B-beta @39a4d50: licence tag apache-2.0. 7,241,748,480 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-03: month the maker's Hugging Face repo was created (createdAt 2024-03-19).

39.8±1.0#534 of 719 LLMsfrom 11 benchmark results across 9 sources

$ how it compares

The LLMs ranked either side of Starling-LM 7B beta, out of 828 with a score, then more from Nexusflow.

#modelscorewhereRAMreleased
624Code Llama 34B Instruct Meta40±1local~22GB2023-08
625Code Llama 34B (base) Meta40±1local~23GB2023-08
626Starling-LM 7B beta Nexusflow40±1local~6GB2024-03
627LFM2 1.2B Liquid AI40±2local~2.2GB2025-07
628Code Tulu 2 13B Allen Institute for AI40±2local~29GB2023-11
more from Nexusflow
290Athene-V2-Chat 72B Nexusflow56±2local~44GB2024-11
401Athene-70B Nexusflow51±1local~29GB2024-07
753NexusRaven V2 13B Nexusflow29±3local~9.3GB2023-12

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #327 of 393 · 33% of its score · 3 tests

Beats OpenThinker3 7B, Gemma 4 E2B, Code Llama 70B Instruct here, though they rank higher overall. Trails LFM2 350M, Gemma 3 1B, Flan-T5 XXL here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena-Hard (v0.1, GPT-4-1106 judge)23.0% ✎▂▁▁▅█▅▄▃▃▅▃▁ beats 18/60medium · avg 52%▇▇▇▇▇▇ 14%sharp
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)1111.0 ✎▂▁▂▁▃▇█▆▇▄▂▂ beats 52/95avg 1201▇▇▇▇ 9.4%blunt
LMArena (text)1170.9 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 50/379avg 1268▇▇▇▇ 9.3%blunt
other tests8 not in a task · 67% of its score
testresultvs the others in its rundifficultycountswhy
LiveBench 2024-07-2616.6% ✎▁▁▁▂▃▃▂█▆▃▅▃ beats 9/61medium · avg 41%▇▇▇▇▇▇▇▇▇▇▇▇ 29%typical
MedQA (USMLE, 4 options)52.5% ✎▁▁··▄▁▁··▄▃█ beats 11/17easy · avg 76%▇▇▇▇▇ 12%sharp · at its level
WildBench v2 WB-Score (task macro)30.1694 WB-Score ✎▁·▁▁·▃█▄▇▆▅▆ beats 15/52avg 45.199 WB-Score▇▇▇▇ 11%sharp
MedMCQA50.2% ✎▂▂··▄▄▂▂·▄██ beats 13/17medium · avg 68%▇▇ 6.2%at its level
Polish EQ-Bench v2 (SpeakLeash)45.1% ✎▁··▁▁▂▂▆▅▆█▆ beats 14/70medium · avg 64%▇▇ 5.4%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)70.9% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 175/276medium · avg 73%▇ 2.0%at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy82.8% ✎▁▁▁▁▁▁▁▂▄█▄▃ beats 81/146easy · avg 83%▇ 1.4%at its level · noisy
PubMedQA78.2% ✎▂·▂▆·▄▂▄▄▂█▃ beats 17/17medium · avg 77%▇ 0.7%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 Starling-LM 7B beta · needs ~4.4 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/Starling-LM-7B-beta-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/Starling-LM-7B-beta-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 Starling-LM 7B beta · needs ~4.4 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/Starling-LM-7B-beta-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 Starling-LM 7B beta · needs ~4.84 GB · from ollama.com
    chat in the terminal
    ollama run starling-lm:7b-beta-q4_K_M

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Starling-LM 7B beta · needs ~4.3 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Starling-LM-7B-beta-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Starling-LM-7B-beta-4bit

Official weights and documentation: huggingface.co/Nexusflow ↗

$ how the score was worked out · LiveBench model judgments (HF… 29%, Open Medical-LLM Leaderboard… 19%, Arena-Hard-Auto v0.1 leaderbo… 14% and 6 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▇▇▇▇▇▇▇▇▇ 29%Apache-2.0 (stated in the LiveBench datasheet)
Open Medical-LLM Leaderboard results (HF dataset openlifescienceai/results)3▇▇▇▇▇▇ 19%Apache-2.0
Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)1▇▇▇▇ 14%Apache-2.0
WildBench v2 leaderboard data (Ai2)1▇▇▇ 11%Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)1▇▇▇ 9%CC-BY-4.0
LMArena leaderboard dataset1▇▇▇ 9%CC BY 4.0
SpeakLeash Polish EQ-Bench leaderboard1▇▇ 5%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 2%Apache-2.0
EuroEval leaderboards (results collection), English generative leaderboard1▇ 1%MIT
prior · pull toward the middle▇ 0%
weighted average= 39.8

$ 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