Instructions to use vanta-research/atom-27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use vanta-research/atom-27b with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vanta-research/atom-27b:F16
# Run inference directly in the terminal:
llama cli -hf vanta-research/atom-27b:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vanta-research/atom-27b:F16
# Run inference directly in the terminal:
llama cli -hf vanta-research/atom-27b:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf vanta-research/atom-27b:F16
# Run inference directly in the terminal:
./llama-cli -hf vanta-research/atom-27b:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf vanta-research/atom-27b:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vanta-research/atom-27b:F16

Use Docker

docker model run hf.co/vanta-research/atom-27b:F16

LM Studio
Jan

vLLM

How to use vanta-research/atom-27b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vanta-research/atom-27b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vanta-research/atom-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vanta-research/atom-27b:F16

Ollama
How to use vanta-research/atom-27b with Ollama:
```
ollama run hf.co/vanta-research/atom-27b:F16
```
Unsloth Desktop
Docker Model Runner
How to use vanta-research/atom-27b with Docker Model Runner:
```
docker model run hf.co/vanta-research/atom-27b:F16
```

Lemonade

How to use vanta-research/atom-27b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vanta-research/atom-27b:F16

Run and chat with the model

lemonade run user.atom-27b-F16

List all available models

lemonade list

Atomic Chat

atom-27b / config.json

unmodeled-tyler

Launching Atom-27B

14ee146 verified 9 months ago

Raw

History Blame Contribute Delete

3.29 kB

	{
	"architectures": [
	"Gemma3ForConditionalGeneration"
	],
	"boi_token_index": 255999,
	"dtype": "bfloat16",
	"eoi_token_index": 256000,
	"eos_token_id": [
	1,
	106
	],
	"image_token_index": 262144,
	"initializer_range": 0.02,
	"mm_tokens_per_image": 256,
	"model_type": "gemma3",
	"text_config": {
	"_sliding_window_pattern": 6,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_logit_softcapping": null,
	"dtype": "bfloat16",
	"final_logit_softcapping": null,
	"head_dim": 128,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 5376,
	"initializer_range": 0.02,
	"intermediate_size": 21504,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention"
	],
	"max_position_embeddings": 131072,
	"model_type": "gemma3_text",
	"num_attention_heads": 32,
	"num_hidden_layers": 62,
	"num_key_value_heads": 16,
	"query_pre_attn_scalar": 168,
	"rms_norm_eps": 1e-06,
	"rope_local_base_freq": 10000.0,
	"rope_scaling": {
	"factor": 8.0,
	"rope_type": "linear"
	},
	"rope_theta": 1000000.0,
	"sliding_window": 1024,
	"use_bidirectional_attention": false,
	"use_cache": true,
	"vocab_size": 262208
	},
	"transformers_version": "4.57.3",
	"use_cache": true,
	"vision_config": {
	"attention_dropout": 0.0,
	"dtype": "bfloat16",
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"image_size": 896,
	"intermediate_size": 4304,
	"layer_norm_eps": 1e-06,
	"model_type": "siglip_vision_model",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 27,
	"patch_size": 14,
	"vision_use_head": false
	}
	}