whatmodel.sh / Arch-Agent-1.5B

Arch-Agent-1.5B

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

Arch-Agent-1.5B is an open-weights language model from Katanemo, released June 2025. Its published size is 1.54B parameters. Licence: other (katanemo-research).

Catalogue identity notes

Maker repo katanemo/Arch-Agent-1.5B @fbb1d58: licence tag other (katanemo-research). 1,543,714,304 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2025-06: month the maker's Hugging Face repo was created (createdAt 2025-06-20).

50.1±4.8#439 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 Arch-Agent-1.5B, out of 1132 with a score, then more from Katanemo.

#modelscorewhereRAMreleased
568FireFunction v2 (70B) Fireworks AI50±6local~24GB2024-06
569Mellum2 12B-A2.5B Instruct JetBrains50±2local~8.6GB2026-05
570Arch-Agent-1.5B Katanemo50±5local~2.4GB2025-06
571OpenCodeInterpreter-DS-33B M-A-P50±1local~22GB2024-02
572GPO-Llama-3-8B-Instruct-GPM-2B general-preference (GPM)50±2local~18GB2024-10
more from Katanemo
328Arch-Agent-32B Katanemo58±5local~21GB2025-06
510Arch-Agent-3B Katanemo52±5local~3.3GB2025-06

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▄▄▃▂▁ #252 of 334 * · 90% of its score · 1 test

Beats o3-mini, Ministral 3 14B Reasoning 2512, DeepSeek R1 0528 Qwen3 8B here, though they rank higher overall. Trails SmolLM3 3B, Phi-3.5-mini-instruct, Jamba 1.5 Mini here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL V4 (December 2025 archive)32.1% ✎▁▁▁▂██▅▅▆▂▂▂ beats 36/77hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%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 Arch-Agent-1.5B · needs ~1 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/Arch-Agent-1.5B-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/Arch-Agent-1.5B-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 Arch-Agent-1.5B · needs ~1 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/Arch-Agent-1.5B-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 Arch-Agent-1.5B · needs ~1 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/Arch-Agent-1.5B-GGUF:Q4_K_M

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 Arch-Agent-1.5B · needs ~0.9 GB, Mac only · from huggingface.co/huangang
    chat in the terminal
    mlx_lm.chat --model huangang/Arch-Agent-1.5B-mlx-4Bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model huangang/Arch-Agent-1.5B-mlx-4Bit

Other ways to run it

  1. Run it as published · needs ~3.09 GB · from huggingface.co/katanemo (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='katanemo/Arch-Agent-1.5B', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/katanemo ↗

$ how the score was worked out · Berkeley Function Calling Lea… 90%

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
Berkeley Function Calling Leaderboard result archive1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%Apache-2.0
prior · pull toward the middle▇▇▇ 10%
weighted average= 50.1

$ 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