whatmodel.sh / SILMA 9B Instruct v1.0

SILMA 9B Instruct v1.0

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

SILMA 9B Instruct v1.0 is an open-weights language model from SILMA AI, released August 2024. Its published size is 9.24B parameters. Licence: gemma.

Catalogue identity notes

Maker repo silma-ai/SILMA-9B-Instruct-v1.0 @d8f4d2b: licence tag gemma. 9,241,705,984 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-08: month the maker's Hugging Face repo was created (createdAt 2024-08-17).

42.1±3.2#667 of 949 LLMsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of SILMA 9B Instruct v1.0, out of 1132 with a score.

#modelscorewhereRAMreleased
824LWM-Text-Chat-1M Large World Model (UC Berkeley)42±5local~5.8GB2024-02
825Jais Family 6p7b (6.7B) Chat Inception (G42)42±3local~32GB2024-08
826SILMA 9B Instruct v1.0 SILMA AI42±3local~7.6GB2024-08
827Claude Instant 1.2 Anthropic42±1comparison only2023-08
828Llama 3 8B Instruct Meta42±0local~6.6GB2024-04

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #311 of 466 * · 65% of its score · 1 test

Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, Ministral 3 8B here, though they rank higher overall. Trails Flan-T5 XXL, LFM2 700M, EXAONE 3.5 2.4B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arabic IFEval prompt-level (Inception)34.2% ✎▁·▁▁▂▁▄▄▆▄█▄ beats 19/38medium · avg 49%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 65%sharp · at its level
other tests1 not in a task · 30% of its score
testresultvs the others in its rundifficultycountswhy
AraGen-v3 3C3H score (Inception, Claude Sonnet 4 judge)6.7% ✎▁▁·▁▃▂▄█▄▅▄▄ beats 5/66hard · avg 31%▇▇▇▇▇▇▇▇▇▇▇▇ 30%typical

$ 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 SILMA 9B Instruct v1.0 · needs ~5.8 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/SILMA-9B-Instruct-v1.0-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/SILMA-9B-Instruct-v1.0-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 SILMA 9B Instruct v1.0 · needs ~5.8 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/SILMA-9B-Instruct-v1.0-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 SILMA 9B Instruct v1.0 · needs ~5.8 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/SILMA-9B-Instruct-v1.0-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~18.48 GB · from huggingface.co/silma-ai (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='silma-ai/SILMA-9B-Instruct-v1.0', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/silma-ai ↗

$ how the score was worked out · Inception Arabic/Hindi leader… 95%

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
Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%Apache-2.0
prior · pull toward the middle▇ 5%
weighted average= 42.1

$ 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