Instructions to use thelamapi/next-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thelamapi/next-12b with Transformers:

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

pipe = pipeline("image-text-to-text", model="thelamapi/next-12b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("thelamapi/next-12b")
model = AutoModelForImageTextToText.from_pretrained("thelamapi/next-12b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use thelamapi/next-12b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="thelamapi/next-12b",
	filename="next-12b-mmproj.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use thelamapi/next-12b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf thelamapi/next-12b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf thelamapi/next-12b:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf thelamapi/next-12b:Q8_0
# Run inference directly in the terminal:
llama-cli -hf thelamapi/next-12b:Q8_0

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 thelamapi/next-12b:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf thelamapi/next-12b:Q8_0

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 thelamapi/next-12b:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf thelamapi/next-12b:Q8_0

Use Docker

docker model run hf.co/thelamapi/next-12b:Q8_0

LM Studio
Jan

vLLM

How to use thelamapi/next-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thelamapi/next-12b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thelamapi/next-12b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/thelamapi/next-12b:Q8_0

SGLang

How to use thelamapi/next-12b 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 "thelamapi/next-12b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thelamapi/next-12b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "thelamapi/next-12b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thelamapi/next-12b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use thelamapi/next-12b with Ollama:
```
ollama run hf.co/thelamapi/next-12b:Q8_0
```

Unsloth Studio new

How to use thelamapi/next-12b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for thelamapi/next-12b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for thelamapi/next-12b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for thelamapi/next-12b to start chatting

Docker Model Runner
How to use thelamapi/next-12b with Docker Model Runner:
```
docker model run hf.co/thelamapi/next-12b:Q8_0
```

Lemonade

How to use thelamapi/next-12b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull thelamapi/next-12b:Q8_0

Run and chat with the model

lemonade run user.next-12b-Q8_0

List all available models

lemonade list

Lamapi commited on Nov 4, 2025

Commit

a4b2a0b

verified ·

1 Parent(s): 1185b62

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -53

README.md CHANGED Viewed

@@ -163,7 +163,7 @@ This model is ideal for **enterprises, researchers, and organizations** who need
   </thead>
   <tbody>
     <tr class="next">
-      <td><strong>Next 14B</strong></td>
       <td><strong>94.6</strong></td>
       <td><strong>93.2</strong></td>
       <td><strong>98.8</strong></td>
@@ -195,58 +195,6 @@ This model is ideal for **enterprises, researchers, and organizations** who need
 ---
-# Next 12B approaches frontier model performance while maintaining efficiency.
-<table>
-  <thead>
-    <tr>
-      <th>Model</th>
-      <th>MMLU (5-shot) %</th>
-      <th>MMLU-Pro %</th>
-      <th>GSM8K %</th>
-      <th>MATH %</th>
-    </tr>
-  </thead>
-  <tbody>
-    <tr class="next">
-      <td data-label="Model">Next Z1</td>
-      <td data-label="MMLU (5-shot) %"><strong>97.3</strong></td>
-      <td data-label="MMLU-Pro %"><strong>94.2</strong></td>
-      <td data-label="GSM8K %">97.7</td>
-      <td data-label="MATH %">93.2</td>
-    </tr>
-    <tr class="next">
-      <td data-label="Model">Next 14B (Thinking)</td>
-      <td data-label="MMLU (5-shot) %">94.6</td>
-      <td data-label="MMLU-Pro %">83.2</td>
-      <td data-label="GSM8K %"><strong>98.8</strong></td>
-      <td data-label="MATH %">92.7</td>
-    </tr>
-    <tr class="next">
-      <td data-label="Model">Next 12B</td>
-      <td data-label="MMLU (5-shot) %">92.7</td>
-      <td data-label="MMLU-Pro %">84.4</td>
-      <td data-label="GSM8K %">95.3</td>
-      <td data-label="MATH %">87.2</td>
-    </tr>
-    <tr>
-      <td data-label="Model">GPT-5</td>
-      <td data-label="MMLU (5-shot) %">92.5</td>
-      <td data-label="MMLU-Pro %">87.0</td>
-      <td data-label="GSM8K %">98.4</td>
-      <td data-label="MATH %"><strong>96.0</strong></td>
-    </tr>
-    <tr>
-      <td data-label="Model">Claude Opus 4.1 (Thinking)</td>
-      <td data-label="MMLU (5-shot) %">~92.0</td>
-      <td data-label="MMLU-Pro %">87.8</td>
-      <td data-label="GSM8K %">84.7</td>
-      <td data-label="MATH %">95.4</td>
-    </tr>
-  </tbody>
-</table>
----
 ## 🚀 Installation & Usage
 ### Use with vision:

   </thead>
   <tbody>
     <tr class="next">
+      <td><strong>Next 14B (Thinking)</strong></td>
       <td><strong>94.6</strong></td>
       <td><strong>93.2</strong></td>
       <td><strong>98.8</strong></td>
 ---
 ## 🚀 Installation & Usage
 ### Use with vision: