Instructions to use llmvision/glimpse-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmvision/glimpse-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="llmvision/glimpse-v1")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("llmvision/glimpse-v1")
model = AutoModelForImageTextToText.from_pretrained("llmvision/glimpse-v1")

llama-cpp-python

How to use llmvision/glimpse-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="llmvision/glimpse-v1",
	filename="glimpse-v1.BF16-mmproj.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use llmvision/glimpse-v1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmvision/glimpse-v1:BF16
# Run inference directly in the terminal:
llama-cli -hf llmvision/glimpse-v1:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf llmvision/glimpse-v1:BF16
# Run inference directly in the terminal:
llama-cli -hf llmvision/glimpse-v1:BF16

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 llmvision/glimpse-v1:BF16
# Run inference directly in the terminal:
./llama-cli -hf llmvision/glimpse-v1:BF16

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 llmvision/glimpse-v1:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmvision/glimpse-v1:BF16

Use Docker

docker model run hf.co/llmvision/glimpse-v1:BF16

LM Studio
Jan

vLLM

How to use llmvision/glimpse-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/llmvision/glimpse-v1:BF16

SGLang

How to use llmvision/glimpse-v1 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 "llmvision/glimpse-v1" \
    --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": "llmvision/glimpse-v1",
		"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 "llmvision/glimpse-v1" \
        --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": "llmvision/glimpse-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use llmvision/glimpse-v1 with Ollama:
```
ollama run hf.co/llmvision/glimpse-v1:BF16
```

Unsloth Studio

How to use llmvision/glimpse-v1 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 llmvision/glimpse-v1 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 llmvision/glimpse-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for llmvision/glimpse-v1 to start chatting

Docker Model Runner
How to use llmvision/glimpse-v1 with Docker Model Runner:
```
docker model run hf.co/llmvision/glimpse-v1:BF16
```

Lemonade

How to use llmvision/glimpse-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmvision/glimpse-v1:BF16

Run and chat with the model

lemonade run user.glimpse-v1-BF16

List all available models

lemonade list

valentinfrlch commited on Apr 27

Commit

b4f2de0

verified ·

1 Parent(s): 2653ad0

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -35

README.md CHANGED Viewed

@@ -13,14 +13,6 @@ tags:
   - on-device
 language:
   - en
-  - de
-  - nl
-  - fr
-  - es
-  - pt
-  - it
-  - pl
-  - sv
 extra_gated_heading: Access Glimpse-v1
 extra_gated_description: >-
   Glimpse-v1 is a Model Derivative of Google's Gemma and is distributed under
@@ -84,7 +76,7 @@ Glimpse-v1 reports a **1.9× accuracy improvement** over the base Gemma 3 4B mod
 ## Training
-- **Base:** Gemma 3 4B (instruction-tuned)
 - **Data:** ~5,000 curated real-world home security camera events spanning diverse scenes, lighting conditions, and event types
 - **Objective:** Supervised fine-tuning for concise, factual event descriptions
@@ -101,45 +93,26 @@ ollama run llmvision/glimpse-v1
 ### Transformers
 ```
 from transformers import AutoProcessor, AutoModelForImageTextToText
 import torch
-model_id = "<your-hf-username>/glimpse-v1"
 processor = AutoProcessor.from_pretrained(model_id)
 model = AutoModelForImageTextToText.from_pretrained(
 model_id, torch_dtype=torch.bfloat16, device_map="auto"
 )
 messages = [
 {"role": "user", "content": [
 {"type": "image", "url": "path/to/frame.jpg"},
 {"type": "text", "text": "Summarize this camera event in one sentence."},
 ]},
 ]
 inputs = processor.apply_chat_template(
 messages, add_generation_prompt=True, tokenize=True,
 return_dict=True, return_tensors="pt",
 ).to(model.device)
 out = model.generate(inputs, max_new_tokens=128)
 print(processor.decode(out[0], skip_special_tokens=True))
 ```
 ## Limitations and risks
@@ -164,17 +137,11 @@ By downloading or using Glimpse-v1 you agree to the Gemma Terms of Use. If you r
 ## Citation
 ```
 @misc{glimpse_v1_2026,
 title  = {Glimpse-v1: A compact vision-language model for home security event understanding},
 author = {LLM Vision},
 year   = {2026},
 url    = {https://llmvision.org/glimpse/}
 }
 ```

   - on-device
 language:
   - en
 extra_gated_heading: Access Glimpse-v1
 extra_gated_description: >-
   Glimpse-v1 is a Model Derivative of Google's Gemma and is distributed under
 ## Training
+- **Base:** Gemma 3 4B
 - **Data:** ~5,000 curated real-world home security camera events spanning diverse scenes, lighting conditions, and event types
 - **Objective:** Supervised fine-tuning for concise, factual event descriptions
 ### Transformers
 ```
 from transformers import AutoProcessor, AutoModelForImageTextToText
 import torch
+model_id = "llmvision/glimpse-v1"
 processor = AutoProcessor.from_pretrained(model_id)
 model = AutoModelForImageTextToText.from_pretrained(
 model_id, torch_dtype=torch.bfloat16, device_map="auto"
 )
 messages = [
 {"role": "user", "content": [
 {"type": "image", "url": "path/to/frame.jpg"},
 {"type": "text", "text": "Summarize this camera event in one sentence."},
 ]},
 ]
 inputs = processor.apply_chat_template(
 messages, add_generation_prompt=True, tokenize=True,
 return_dict=True, return_tensors="pt",
 ).to(model.device)
 out = model.generate(inputs, max_new_tokens=128)
 print(processor.decode(out[0], skip_special_tokens=True))
 ```
 ## Limitations and risks
 ## Citation
 ```
 @misc{glimpse_v1_2026,
 title  = {Glimpse-v1: A compact vision-language model for home security event understanding},
 author = {LLM Vision},
 year   = {2026},
 url    = {https://llmvision.org/glimpse/}
 }
 ```