Instructions to use spectator2026/Infinity-Parser2-Flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spectator2026/Infinity-Parser2-Flash-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="spectator2026/Infinity-Parser2-Flash-GGUF",
	filename="Infinity-Parser2-Flash-Q6_K.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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use spectator2026/Infinity-Parser2-Flash-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K
# Run inference directly in the terminal:
llama-cli -hf spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K
# Run inference directly in the terminal:
llama-cli -hf spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K

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 spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K

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 spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K

Use Docker

docker model run hf.co/spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K

LM Studio
Jan

vLLM

How to use spectator2026/Infinity-Parser2-Flash-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "spectator2026/Infinity-Parser2-Flash-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "spectator2026/Infinity-Parser2-Flash-GGUF",
		"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/spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K

Ollama
How to use spectator2026/Infinity-Parser2-Flash-GGUF with Ollama:
```
ollama run hf.co/spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K
```

Unsloth Studio

How to use spectator2026/Infinity-Parser2-Flash-GGUF 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 spectator2026/Infinity-Parser2-Flash-GGUF 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 spectator2026/Infinity-Parser2-Flash-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for spectator2026/Infinity-Parser2-Flash-GGUF to start chatting

How to use spectator2026/Infinity-Parser2-Flash-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use spectator2026/Infinity-Parser2-Flash-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K

Run Hermes

hermes

Docker Model Runner
How to use spectator2026/Infinity-Parser2-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K
```

Lemonade

How to use spectator2026/Infinity-Parser2-Flash-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull spectator2026/Infinity-Parser2-Flash-GGUF:Q6_K

Run and chat with the model

lemonade run user.Infinity-Parser2-Flash-GGUF-Q6_K

List all available models

lemonade list

Infinity-Parser2-Flash-GGUF / README.md

spectator2026

Upload folder using huggingface_hub

93486da verified 3 days ago

preview code

raw

history blame contribute delete

2.54 kB

	---
	license: apache-2.0
	base_model: infly/Infinity-Parser2-Flash
	pipeline_tag: image-text-to-text
	library_name: gguf
	language:
	- en
	- zh
	tags:
	- ocr
	- document-parsing
	- document-understanding
	- vlm
	- vision-language
	- gguf
	- llama.cpp
	- q6_k
	- imatrix
	- quantized
	---

	# Infinity-Parser2-Flash — Q6_K GGUF (+ vision mmproj)

	A Q6_K GGUF quantization of [`infly/Infinity-Parser2-Flash`](https://huggingface.co/infly/Infinity-Parser2-Flash) for llama.cpp / `llama-server`, so the model runs on a single consumer GPU (validated on an RTX 3080 Ti, 12 GB) without vLLM. ~4.2 GB bf16 → ~1.5 GB Q6_K weights (+ 0.67 GB f16 vision projector).

	The base is a Qwen3.5-architecture vision-language model for document understanding: OCR, layout analysis, tables→HTML, charts→JSON, formulas→LaTeX, and Markdown conversion (EN/ZH).

	## Files
	\| File \| What \|
	\|---\|---\|
	\| `Infinity-Parser2-Flash-Q6_K.gguf` \| Q6_K-quantized weights (imatrix) \|
	\| `Infinity-Parser2-Flash-mmproj-f16.gguf` \| f16 multimodal projector — required for image input \|

	## Method
	`convert_hf_to_gguf` → f16 GGUF → `llama-quantize Q6_K` with an importance matrix computed from a clean native-PDF document corpus (~519 k tokens). (`llama-imatrix` is text-only; the mmproj carries the vision tower at serve time.)

	## Quality (VLMEvalKit, vs published bf16)
	\| Benchmark \| bf16 \| Q6_K GGUF \|
	\|---\|---\|---\|
	\| DocVQA (val) \| 93.80 \| 93.63 \|
	\| OCRBench \| 84.3 \| 82.8 \|
	\| MMStar / MMBench \| ref \| ≥ bf16 \|

	Effectively lossless for the 6-bit quant. The small OCRBench dip is not the quantization — an f16 GGUF on the same stack scores ≈ 83.0 ≈ Q6_K's 82.8, so the residual gap is the llama.cpp vision preprocessing (candle CLIP), not the 6-bit weights.

	## Serving (llama.cpp)
	```bash
	llama-server \
	--model Infinity-Parser2-Flash-Q6_K.gguf \
	--mmproj Infinity-Parser2-Flash-mmproj-f16.gguf \
	--ctx-size 32768 --n-gpu-layers 99 \
	--host 0.0.0.0 --port 8105
	```
	OpenAI-compatible `/v1/chat/completions` with `image_url` content. Notes:
	- Reasoning-capable model: output may arrive in the `reasoning_content` channel (llama.cpp routes the think block there) — read it accordingly, or disable thinking.
	- A 16 MP page ≈ 15.6 K vision tokens, so `--ctx-size 32768` comfortably fits one page + output.

	---
	Quantized by [@spectator2026](https://huggingface.co/spectator2026). Original model © infly, Apache-2.0 — see the [base model card](https://huggingface.co/infly/Infinity-Parser2-Flash).