Instructions to use Fazmin/solus_v1_unlimited-ocr-q5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Fazmin/solus_v1_unlimited-ocr-q5 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 Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M

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 Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M

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 Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M

Use Docker

docker model run hf.co/Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M

LM Studio
Jan

vLLM

How to use Fazmin/solus_v1_unlimited-ocr-q5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fazmin/solus_v1_unlimited-ocr-q5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fazmin/solus_v1_unlimited-ocr-q5",
		"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/Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M

Ollama
How to use Fazmin/solus_v1_unlimited-ocr-q5 with Ollama:
```
ollama run hf.co/Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Fazmin/solus_v1_unlimited-ocr-q5 with Docker Model Runner:
```
docker model run hf.co/Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M
```

Lemonade

How to use Fazmin/solus_v1_unlimited-ocr-q5 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Fazmin/solus_v1_unlimited-ocr-q5:Q5_K_M

Run and chat with the model

lemonade run user.solus_v1_unlimited-ocr-q5-Q5_K_M

List all available models

lemonade list

Atomic Chat

Unlimited OCR 3B (Q5_K_M) — Solus v1

baidu's Unlimited-OCR converted to GGUF: a SAM + CLIP "DeepEncoder" vision tower feeding a DeepSeek MoE text decoder, for multilingual OCR and document parsing. It reads a page image and returns markdown, with grounding markers that Solus strips before showing the text. Built on the DeepSeek-OCR stack, but its own model: a ring sliding-window KV cache keeps the full image prefill resident while rotating only recent decode tokens, which is what lets it run long documents without unbounded KV growth.

This is the Q5_K_M build, the more accurate of the two readers in the Solus catalogue. It ships with a multimodal projector (mmproj) that must be loaded alongside the weights; without it the model loads but sees nothing. Needs a llama.cpp with DeepSeek-OCR support (merged upstream in PR #17400); the projector declares clip.projector_type = deepseekocr and the weights general.architecture = deepseek2-ocr.

Specifications


Parameters	3B
Quantization	Q5_K_M
File size	2.82 GB
Minimum RAM	6.00 GB
Minimum VRAM	not required
Context length	8,192 tokens
SHA-256	`3f3fc21627c8998cc5b9f682d913ad392f84f72d7037ab465f50a1c8c46d02c2`

Single file: Unlimited-OCR-Q5_K_M.gguf

Quantization

Quantization performed at the Faculty of Engineering, McMaster University.

The conversion this build is derived from was produced by sahilchachra, and the weights here are a byte-for-byte copy of that file — the SHA-256 above matches the upstream artifact.

Provenance

Original model: baidu/Unlimited-OCR
Upstream GGUF: sahilchachra/Unlimited-OCR-GGUF
Mirrored for Solus, a desktop app for running language models entirely on your own machine.

Usage

llama-cli -m Unlimited-OCR-Q5_K_M.gguf -cnv

License

Licensed MIT.

Downloads last month: 43

GGUF

Model size

3B params

Architecture

deepseek2-ocr

Hardware compatibility

5-bit

Model tree for Fazmin/solus_v1_unlimited-ocr-q5

Base model

baidu/Unlimited-OCR

Quantized

(34)

this model