whatmodel.sh / Apriel 1.6 15B Thinker

Apriel 1.6 15B Thinker

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

Apriel 1.6 15B Thinker is an open-weights language model from ServiceNow, released November 2025. Its published size is 14.9B parameters. Licence: mit.

61.7±1.5#182 of 719 LLMsfrom 7 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Apriel 1.6 15B Thinker, out of 828 with a score.

#modelscorewhereRAMreleased
212Gemini 2.0 Flash-Lite (001) Google62±2comparison only2025-02
213Mistral Large 3 (675B-A41B) Mistral62±1api $0.75/M +local~108GB2025-12
214Apriel 1.6 15B Thinker ServiceNow62±2local~10GB2025-11
215Gemini 2.5 Flash-Lite Preview (06-17) Google62±2comparison only2025-06
216Gemini 2.5 Flash Google62±1api $0.85/M2025-06

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #195 of 300 · 31% of its score · 3 tests

Beats o1 (2024-12-17), o3-mini, DeepSeek R1 (Jan '25) here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Mellum2 12B-A2.5B Instruct here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
τ²-bench Retail lab66.7% ✎█▄··▄··▄·▄·▄ beats 3/6medium · avg 37%▇▇▇▇▇ 13%at its level
SWE-bench Verified lab23.0% ✎█·█▄·······█ beats 1/6very hard · avg 11%▇▇▇▇ 10%sharp · at its level
τ²-bench Airline lab58.0% ✎▄▄······▄█▄▄ beats 4/6hard · avg 29%▇▇▇▇ 9.1%at its level
coding▁▁▁▃▆██▇▆▄▃▁ #176 of 458 * · 61% of its score · 2 tests

Beats Qwen3.5 9B, Devstral 2 (2512) here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 8B Reasoning 2512, Phi-4-reasoning 14B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Aider polyglot (225 exercises, two attempts) lab37.7% ✎█▄····▄··█·▄ beats 0/6very hard · avg 7.9%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 52%sharp · at its level
SWE-bench Verified lab23.0% ✎█·█▄·······█ beats 1/6very hard · avg 11%▇▇▇▇ 10%sharp · at its level
vision & documents▁▁▃▂▁▃▄▃▆▇█▄ #89 of 147 * · 11% of its score · 2 tests

Beats DeepSeek V4 Flash Vision (Exp), GPT-5 nano here, though they rank higher overall. Trails Mistral Small 4 (119B-A6.5B), Qwen3-VL 32B Instruct, GPT-4.1 mini here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
CharXiv (reasoning questions) lab56.0% ✎▄·····▄▄·▄·█ beats 1/5hard · avg 33%▇▇▇ 6.6%at its level
CharXiv descriptive questions lab89.8% ✎▄····▄···█▄▄ beats 2/5easy · avg 68%▇▇ 4.0%noisy
other tests1 not in a task · 5.2% of its score
testresultvs the others in its rundifficultycountswhy
Multi-IF (aggregation unspecified) lab83.3% ✎▄·····▄█▄▄·▄ beats 3/6easy · avg 66%▇▇ 5.2%blunt

$ 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 Apriel 1.6 15B Thinker · needs ~9.44 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/ServiceNow-AI_Apriel-1.6-15b-Thinker-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/ServiceNow-AI_Apriel-1.6-15b-Thinker-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 Apriel 1.6 15B Thinker · needs ~9.44 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/ServiceNow-AI_Apriel-1.6-15b-Thinker-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 Apriel 1.6 15B Thinker · needs ~9.44 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/ServiceNow-AI_Apriel-1.6-15b-Thinker-GGUF: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 Apriel 1.6 15B Thinker · needs ~8.1 GB, Mac only · from huggingface.co/cnfusion
    chat in the terminal
    mlx_lm.chat --model cnfusion/Apriel-1.6-15b-Thinker-mlx-4Bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model cnfusion/Apriel-1.6-15b-Thinker-mlx-4Bit

Weights and documentation: huggingface.co/ServiceNow-AI ↗

$ how the score was worked out · ServiceNow-AI/Apriel-1.6-15b-… 99%

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
ServiceNow-AI/Apriel-1.6-15b-Thinker model card · lab-reported7▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%MIT
prior · pull toward the middle▇ 1%
weighted average= 61.7

$ 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