whatmodel.sh / Ling-lite-1.5
Ling-lite-1.5
↗ share
+ contribute
Ling-lite-1.5 is an open-weights language model from inclusionAI (Ant Group), released May 2025. Its published size is 16.8B parameters (2.75B active per token). Licence: mit.
Catalogue identity notes
Maker repo inclusionAI/Ling-lite-1.5 @ef1ac33: licence tag mit. 16,801,974,272 parameters from the Hugging Face safetensors metadata; active 2.75B per token (Ling card: 'Ling-lite has 16.8 billion parameters with 2.75 billion activated parameters'). Released 2025-05: month the maker's Hugging Face repo was created (createdAt 2025-05-11).
$ how it compares
The LLMs ranked either side of Ling-lite-1.5, out of 1132 with a score, then more from inclusionAI (Ant Group).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 517 |  Llama 3.1 Nemotron 70B Instruct | 52±1 | local | ||
| 518 |  Palmyra X4 (palmyra-x-004) | 52±4 | comparison only | ||
| 519 | Ling-lite-1.5 | 52±6 | local | ||
| 520 | Nemotron-4 340B Instruct | 52±2 | comparison only | ||
| 521 |  Aya Expanse 32B | 52±2 | api $0.75/M +local | ||
| more from inclusionAI (Ant Group) | |||||
| 87 | Ling 3.0 Flash (124B-A5B) | 71±2 | api $0.090/M +local | ||
| 111 | Ring-2.6-1T | 69±2 | comparison only | ||
| 310 | Ling-flash-2.0 | 59±2 | local | ||
$ what it's good at
agent tasks▁▁▃▆█▆▅▄▄▃▂▁ #259 of 334 * · 82% 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 Granite 4.0 1B, SmolLM3 3B, Phi-3.5-mini-instruct here, though they rank lower overall.
$ where to run it
llama.cpp · recommended
version
- 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 | shWindowsirm https://llama.app/install.ps1 | iex - Run Ling-lite-1.5 · needs ~11.2 GB · from huggingface.co/mradermacherchat in the terminal
llama cli -hf mradermacher/Ling-lite-1.5-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf mradermacher/Ling-lite-1.5-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run Ling-lite-1.5 · needs ~11.2 GB · from huggingface.co/mradermacher
- Or download it in the terminal
lms get https://huggingface.co/mradermacher/Ling-lite-1.5-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
version
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run Ling-lite-1.5 · needs ~11.2 GB · from huggingface.co/mradermacherchat in the terminal
ollama run hf.co/mradermacher/Ling-lite-1.5-GGUF:Q4_K_M
Other ways to run it
- Run it as published · needs ~33.6 GB · from huggingface.co/inclusionAI (official)
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='inclusionAI/Ling-lite-1.5', torch_dtype='auto', device_map='auto', trust_remote_code=True)('Once upon a time', max_new_tokens=40)[0]['generated_text'])"
Official weights and documentation: huggingface.co/inclusionAI ↗
$ how the score was worked out · Berkeley Function Calling Lea… 82%
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
| source | results | share of the score |
|---|---|---|
 Berkeley Function Calling Leaderboard result archive | 1 | 82% |
| prior · pull toward the middle | 18% | |
| weighted average | = 51.8 |
$ improve this page
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