Image-Text-to-Text
GGUF
English
Portuguese
ollama
llama.cpp
local-ai
on-device
low-vram
4gb-vram
small-model
tiny-llm
vision
multimodal
thinking
reasoning
chain-of-thought
distillation
tool-calling
qwen
qwen-4b
4b
qwen3.8
qwen3.5
iq3_xxs
imatrix
experimental
conversational
Eval Results (legacy)
Instructions to use sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF 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 sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS # Run inference directly in the terminal: llama cli -hf sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS # Run inference directly in the terminal: llama cli -hf sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS # Run inference directly in the terminal: ./build/bin/llama cli -hf sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
Use Docker
docker model run hf.co/sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
- Llama new
- LM Studio
- Jan
- vLLM
How to use sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sysrobson/Qwen-4B-Bugio-Vision-Thinking-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": "sysrobson/Qwen-4B-Bugio-Vision-Thinking-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/sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
- Ollama
How to use sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF with Ollama:
ollama run hf.co/sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
- Unsloth Desktop
- Pi
How to use sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF with Docker Model Runner:
docker model run hf.co/sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
- Lemonade
How to use sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
Run and chat with the model
lemonade run user.Qwen-4B-Bugio-Vision-Thinking-GGUF-IQ3_XXS
List all available models
lemonade list
- Hermes Agent
How to use sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
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://127.0.0.1:9931/v1 hermes config set model.default sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF:IQ3_XXS" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download benchmarks/thinking.json from sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 8.2 kB
-
https://huggingface.co/sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF/resolve/main/benchmarks/thinking.json
- Command line
-
hf download hf://sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF/benchmarks/thinking.json
-
curl -L -o thinking.json https://huggingface.co/sysrobson/Qwen-4B-Bugio-Vision-Thinking-GGUF/resolve/main/benchmarks/thinking.json
8.2 kB
| { | |
| "bugio-4b": { | |
| "correct": 5, | |
| "total": 5, | |
| "tokens": 7234, | |
| "seconds": 507.3, | |
| "rows": [ | |
| { | |
| "prompt": "A train leaves at 14:35 and arrives at 17:10. How long is the trip in minutes?", | |
| "expected": "155", | |
| "correct": true, | |
| "tokens": 457, | |
| "seconds": 33.4, | |
| "content": "The trip is **155 minutes** long.\n\nHere is the breakdown:\n1. **Hours:** $17 - 14 = 3$ hours.\n2. **Minutes:** $10 - 35 = -25$ (so we borrow 1 hour).\n * $3 \\text{ hours} - 1 \\text{ hour} = 2 \\text{ hours}$\n * $60 \\text{ minutes} + 10 - 35 = 35 \\text{ minutes}$\n3. **Total time:** $2 \\text{ hours} \\times 60 \\text{ minutes} + 35 \\text{ minutes} = 155 \\text{ minutes}$." | |
| }, | |
| { | |
| "prompt": "I have 3 boxes with 12 pens each. I give away 7 pens and buy 2 packs of 5. How many pens do I have?", | |
| "expected": "39", | |
| "correct": true, | |
| "tokens": 492, | |
| "seconds": 34.8, | |
| "content": "Here is the step-by-step breakdown:\n\n1. **Start:** You have 3 boxes with 12 pens each.\n $3 \\times 12 = 36$ pens.\n\n2. **Give away 7:**\n $36 - 7 = 29$ pens.\n\n3. **Buy 2 packs of 5 (10 pens total):**\n $29 + 10 = 39$ pens.\n\nYou have **39** pens." | |
| }, | |
| { | |
| "prompt": "A shirt costs $40 after a 20% discount. What was the original price in dollars?", | |
| "expected": "50", | |
| "correct": true, | |
| "tokens": 535, | |
| "seconds": 37.8, | |
| "content": "The original price of the shirt was **$50**.\n\nHere is the step-by-step breakdown:\n\n1. A 20% discount means the customer pays 80% of the original price.\n2. Set up the equation: $0.80 \\times \\text{Original Price} = \\$40$\n3. Solve for the original price:\n $$\\text{Original Price} = \\$40 / 0.80 = \\$50$$\n\nYou can verify this: 20% of $50 is $10, and $50 - $10 = $40." | |
| }, | |
| { | |
| "prompt": "If 5 machines make 5 widgets in 5 minutes, how many minutes do 100 machines take to make 100 widgets?", | |
| "expected": "5", | |
| "correct": true, | |
| "tokens": 5051, | |
| "seconds": 353.3, | |
| "content": "The answer is **5 minutes**.\n\nHere is the step-by-step reasoning:\n\n1. **Determine the rate:** The statement \"5 machines make 5 widgets in 5 minutes\" tells us the rate. Since 5 machines produce 5 widgets in 5 minutes, each machine works independently, meaning **1 machine makes 1 widget in 5 minutes**.\n2. **Apply the rate to the new scenario:** We need 100 machines to make 100 widgets. Since the rate is 1 widget per machine per 5 minutes, 100 machines will make 100 widgets in the same amount of time.\n3. **Conclusion:** It takes **5 minutes**." | |
| }, | |
| { | |
| "prompt": "What is the sum of all even numbers from 2 to 50 inclusive?", | |
| "expected": "650", | |
| "correct": true, | |
| "tokens": 699, | |
| "seconds": 48.0, | |
| "content": "The sum of all even numbers from 2 to 50 inclusive is **650**.\n\nHere is the step-by-step breakdown:\n\n1. **Identify the sequence:** The even numbers are $2, 4, 6, \\dots, 50$.\n2. **Determine the number of terms ($n$):**\n The formula for the $n$-th term of an arithmetic sequence is $a_n = a_1 + (n-1)d$.\n $50 = 2 + (n-1)2$\n $48 = 2(n-1)$\n $24 = n - 1$\n $n = 25$\n There are **25** terms in the sequence.\n3. **Calculate the sum:**\n Using the formula for the sum of an arithmetic series: $S_n = \\frac{n}{2}(a_1 + a_n)$\n $$S_{25} = \\frac{25}{2}(2 + 50) = \\frac{25 \\times 52}{2} = 25 \\times 26 = 650$$\n\n**Answer:** 650" | |
| } | |
| ] | |
| }, | |
| "sagui-4b": { | |
| "correct": 5, | |
| "total": 5, | |
| "tokens": 13928, | |
| "seconds": 990.1, | |
| "rows": [ | |
| { | |
| "prompt": "A train leaves at 14:35 and arrives at 17:10. How long is the trip in minutes?", | |
| "expected": "155", | |
| "correct": true, | |
| "tokens": 3003, | |
| "seconds": 212.1, | |
| "content": "To find the duration of the trip in minutes, we can calculate the total number of minutes from a common reference point (midnight) for both times and then subtract.\n\n**Step 1: Convert start time to minutes**\nThe train leaves at 14:35.\n$14 \\text{ hours} \\times 60 \\text{ minutes/hour} = 840 \\text{ minutes}$\n$840 + 35 = 875 \\text{ minutes}$\n\n**Step 2: Convert arrival time to minutes**\nThe train arrives at 17:10.\n$17 \\text{ hours} \\times 60 \\text{ minutes/hour} = 1020 \\text{ minutes}$\n$1020 + 10 = 1030 \\text{ minutes}$\n\n**Step 3: Calculate the difference**\nSubtract the departure time from the arrival time.\n$1030 - 875 = 155 \\text{ minutes}$\n\nAlternatively, you can calculate it as 2 hours and 35 minutes ($16:35 + 35 \\text{ mins} = 17:10$), which is $120 + 35 = 155$ minutes.\n\n**Answer:**\nThe trip is **155** minutes long." | |
| }, | |
| { | |
| "prompt": "I have 3 boxes with 12 pens each. I give away 7 pens and buy 2 packs of 5. How many pens do I have?", | |
| "expected": "39", | |
| "correct": true, | |
| "tokens": 707, | |
| "seconds": 49.3, | |
| "content": "Here is the step-by-step calculation:\n\n1. **Start:** You have 3 boxes with 12 pens each.\n $3 \\times 12 = 36$ pens.\n\n2. **Action 1:** You give away 7 pens.\n $36 - 7 = 29$ pens remaining.\n\n3. **Action 2:** You buy 2 packs of 5 pens.\n $2 \\times 5 = 10$ new pens.\n\n4. **Total:** Add the new pens to your remaining ones.\n $29 + 10 = 39$ pens.\n\nYou have **39** pens." | |
| }, | |
| { | |
| "prompt": "A shirt costs $40 after a 20% discount. What was the original price in dollars?", | |
| "expected": "50", | |
| "correct": true, | |
| "tokens": 1504, | |
| "seconds": 102.5, | |
| "content": "The original price was **$50**.\n\nHere is the breakdown:\n1. A 20% discount means the customer pays 80% of the original price ($100\\% - 20\\% = 80\\%$).\n2. Set up the equation: $0.80 \\times \\text{Original Price} = \\$40$.\n3. Solve for the Original Price: $\\$40 \\div 0.80 = \\$50$.\n\n**Check:** A 20% discount on $50 is $10. Subtracting that from the original price ($50 - $10) leaves you with $40." | |
| }, | |
| { | |
| "prompt": "If 5 machines make 5 widgets in 5 minutes, how many minutes do 100 machines take to make 100 widgets?", | |
| "expected": "5", | |
| "correct": true, | |
| "tokens": 7414, | |
| "seconds": 537.6, | |
| "content": "The answer is **5 minutes**.\n\nHere is the step-by-step breakdown:\n\n1. **Determine the rate:** In the first scenario, 5 machines produce 5 widgets in 5 minutes. This means that for every 5 minutes of work, each machine produces exactly 1 widget (assuming they work independently and simultaneously).\n2. **Analyze the new scenario:** We now have 100 machines and we need to make 100 widgets.\n3. **Apply the rate:** Since each machine still needs to produce 1 widget, and it takes 5 minutes for one machine to do that, the time required does not change regardless of how many machines are working in parallel.\n4. **Conclusion:** With the ratio of machines to widgets remaining the same ($1:1$), the total time required remains **5 minutes**.\n\nMathematically, if $W = \\frac{M \\times T}{T_{total}}$, then for the first case $5 = \\frac{5 \\times 5}{5}$ (assuming 1 machine makes 1 widget in 5 mins). For the second case, since the number of machines and widgets both increased by a factor of 20 ($100/5 = 20$), the time required stays the same.\n\nAnswer: **5 minutes**." | |
| }, | |
| { | |
| "prompt": "What is the sum of all even numbers from 2 to 50 inclusive?", | |
| "expected": "650", | |
| "correct": true, | |
| "tokens": 1300, | |
| "seconds": 88.6, | |
| "content": "To find the sum of all even numbers from 2 to 50 inclusive, we can treat this as an arithmetic series.\n\n**1. Identify the terms:**\nThe sequence is $2, 4, 6, ..., 50$.\n* First term ($a_1$) = 2\n* Last term ($a_n$) = 50\n* Common difference = 2\n\n**2. Determine the number of terms ($n$):**\nUsing the formula $n = \\frac{\\text{last} - \\text{first}}{\\text{difference}} + 1$:\n$$n = \\frac{50 - 2}{2} + 1$$\n$$n = \\frac{48}{2} + 1$$\n$$n = 24 + 1 = 25$$\nThere are 25 terms in this sequence.\n\n**3. Calculate the sum:**\nUsing the arithmetic series sum formula: $S_n = \\frac{n}{2}(a_1 + a_n)$\n\n$$S_{25} = \\frac{25}{2}(2 + 50)$$\n$$S_{25} = \\frac{25}{2}(52)$$\n$$S_{25} = 25 \\times 26$$\n$$S_{25} = 650$$\n\n**Answer:**\nThe sum is **650**." | |
| } | |
| ] | |
| } | |
| } |