Instructions to use yandex/AliceAI-Foundation-80B-A3B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yandex/AliceAI-Foundation-80B-A3B-Base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="yandex/AliceAI-Foundation-80B-A3B-Base", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("yandex/AliceAI-Foundation-80B-A3B-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yandex/AliceAI-Foundation-80B-A3B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yandex/AliceAI-Foundation-80B-A3B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yandex/AliceAI-Foundation-80B-A3B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yandex/AliceAI-Foundation-80B-A3B-Base

SGLang

How to use yandex/AliceAI-Foundation-80B-A3B-Base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "yandex/AliceAI-Foundation-80B-A3B-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yandex/AliceAI-Foundation-80B-A3B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "yandex/AliceAI-Foundation-80B-A3B-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yandex/AliceAI-Foundation-80B-A3B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yandex/AliceAI-Foundation-80B-A3B-Base with Docker Model Runner:
```
docker model run hf.co/yandex/AliceAI-Foundation-80B-A3B-Base
```

35B

by Rekss13 - opened about 22 hours ago

Discussion

Rekss13

about 22 hours ago

Ждем в версии 35B, чтоб можно было на 12 vram + 32 ram использовать

alexkhv

about 22 hours ago

qwen3 next flash вышла в декабре 2025, через 9 месяцев родили aliceai 80b a3b.
qwen3.5 35b вышла в марте 2026, вот и делайте выводы.

MaskinSin

about 15 hours ago

Ждем в версии 35B, чтоб можно было на 12 vram + 32 ram использовать

так уже выпустила яндекс, 35B A0.6B посмотри в профиле

TreeLoys

about 13 hours ago

•

edited about 13 hours ago

так уже выпустила яндекс, 35B A0.6B посмотри в профиле

Так интересно A3B, а не A0.6B. т.к. в llm-server ты раскидываешь только активные слои в GPU, в итоге у тебя 0,6b будут около 2-4 гигов занимать и не раскрывать потенциал карточек 12gb vram, а качество 0,6gb активных заметно хуже будет A3B.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment