Instructions to use saidutta69/Qwen3-VL-2B-Instruct-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saidutta69/Qwen3-VL-2B-Instruct-heretic with Transformers:

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

pipe = pipeline("image-text-to-text", model="saidutta69/Qwen3-VL-2B-Instruct-heretic")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("saidutta69/Qwen3-VL-2B-Instruct-heretic")
model = AutoModelForMultimodalLM.from_pretrained("saidutta69/Qwen3-VL-2B-Instruct-heretic", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use saidutta69/Qwen3-VL-2B-Instruct-heretic 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 saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_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 saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_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 saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M

Use Docker

docker model run hf.co/saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M

LM Studio
Jan

vLLM

How to use saidutta69/Qwen3-VL-2B-Instruct-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saidutta69/Qwen3-VL-2B-Instruct-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saidutta69/Qwen3-VL-2B-Instruct-heretic",
		"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/saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M

SGLang

How to use saidutta69/Qwen3-VL-2B-Instruct-heretic 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 "saidutta69/Qwen3-VL-2B-Instruct-heretic" \
    --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": "saidutta69/Qwen3-VL-2B-Instruct-heretic",
		"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 "saidutta69/Qwen3-VL-2B-Instruct-heretic" \
        --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": "saidutta69/Qwen3-VL-2B-Instruct-heretic",
		"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 saidutta69/Qwen3-VL-2B-Instruct-heretic with Ollama:
```
ollama run hf.co/saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M
```
Unsloth Desktop

How to use saidutta69/Qwen3-VL-2B-Instruct-heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M

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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use saidutta69/Qwen3-VL-2B-Instruct-heretic with Docker Model Runner:
```
docker model run hf.co/saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M
```

Lemonade

How to use saidutta69/Qwen3-VL-2B-Instruct-heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-VL-2B-Instruct-heretic-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use saidutta69/Qwen3-VL-2B-Instruct-heretic with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M

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 saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use saidutta69/Qwen3-VL-2B-Instruct-heretic with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M

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://127.0.0.1:8080/v1 \
  --custom-model-id "saidutta69/Qwen3-VL-2B-Instruct-heretic:Q4_K_M" \
  --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"

Qwen3-VL-2B-Instruct-heretic

A decensored variant of Qwen/Qwen3-VL-2B-Instruct, produced with Heretic v1.4.0 (directional ablation / "abliteration"). Qwen3-VL is the vision-language branch of the Qwen3 family — image, video, and OCR input with spatial grounding — and refusal behaviour is suppressed here via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the vision tower and grounding behaviour are left largely intact.

Who this is for: developers who want uncensored vision-language understanding on hardware they already own. At 2B this is the smallest model in the collection that still sees images, and it answers directly instead of declining — refusals drop from 97/100 to 5/100. Best for local OCR, screenshot and document Q&A, UI-to-code from a reference image, and vision agents on CPU or a low-VRAM GPU. If you need text-only at this size, Qwen2.5-3B-Instruct-heretic is the denser sibling.

Runs on your gaming PC

Full GGUF ladder included - pick the quant that fits your card:

Your GPU	Recommended quant	Weights
RTX 4090 / 5090 (24 GB)	Q8_0	1.71 GB
RTX 4080 / 5080 / 4060 Ti 16G (16 GB)	Q6_K	1.32 GB
RTX 3060 / 4070 / 5070 (12 GB)	Q5_K_M	1.17 GB
RTX 4060 / 3070 (8 GB)	Q4_K_M	1.03 GB
GTX 1660 Super / 2060 / 3050 laptop (6 GB)	IQ4_XS	0.95 GB
CPU-only / Apple Silicon	Q4_K_M	1.03 GB

Weights only, at this model's native 2B size; add ~1 GB per 32K of context. Multimodal context carries image tokens too, so budget more KV cache than a text-only model of the same size. OOM? Drop one quant level. Headroom to spare? Go one up.

Abliteration parameters

Trial 74 of a 200-trial Heretic run (seed 1736045380). direction_index was selected per layer.

Parameter	Value
direction_index	per layer
attn.o_proj.max_weight	1.25
attn.o_proj.max_weight_position	26.80
attn.o_proj.min_weight	0.97
attn.o_proj.min_weight_distance	14.91
mlp.down_proj.max_weight	1.25
mlp.down_proj.max_weight_position	22.23
mlp.down_proj.min_weight	0.90
mlp.down_proj.min_weight_distance	6.95

Performance

Metric	This model	Original model (Qwen/Qwen3-VL-2B-Instruct)
KL divergence	0.0528	0 (by definition)
Refusals	5/100	97/100

KL divergence of 0.0528 with refusals at 5/100 is one of the stronger trade-offs in this batch: the harmful evaluation set drops from 97/100 to 5/100 while the vision tower and grounding behaviour stay close to the original. Small models concentrate refusal behaviour into fewer directions, which is why a 2B edit can land this cleanly.

Why abliteration instead of fine-tuning

Fine-tuning a "helpful" persona on top of RLHF'd refusals fights the base model's training and tends to degrade coherence. Abliteration instead finds and edits the specific weight directions responsible for refusal, leaving the rest of the network (and its capabilities) untouched. See the Heretic repo and the original abliteration writeup for the mechanism.

Made with ❤️ by RACER IS OP — follow for more uncensored models

Files

Safetensors

File	Size
`model.safetensors`	3.96 GB

BF16, ~2B. The reproduce/ directory carries the full Heretic recipe - config.toml, requirements.txt, the Optuna study journal, and SHA-256 sums - so this exact model can be regenerated bit-for-bit. Reproduce it with heretic --reproduce reproduce/reproduce.json.

GGUF quantizations

Full quantization set (14 quants + F16) produced with llama.cpp.

File	Format	Size
`Qwen3-VL-2B-Instruct-heretic-F16.gguf`	GGUF F16	3.21 GB
`Qwen3-VL-2B-Instruct-heretic-Q2_K.gguf`	GGUF Q2_K	0.72 GB
`Qwen3-VL-2B-Instruct-heretic-IQ3_S.gguf`	GGUF IQ3_S	0.81 GB
`Qwen3-VL-2B-Instruct-heretic-Q3_K_S.gguf`	GGUF Q3_K_S	0.81 GB
`Qwen3-VL-2B-Instruct-heretic-Q3_K_M.gguf`	GGUF Q3_K_M	0.88 GB
`Qwen3-VL-2B-Instruct-heretic-Q3_K_L.gguf`	GGUF Q3_K_L	0.93 GB
`Qwen3-VL-2B-Instruct-heretic-IQ4_XS.gguf`	GGUF IQ4_XS	0.95 GB
`Qwen3-VL-2B-Instruct-heretic-Q4_K_S.gguf`	GGUF Q4_K_S	0.99 GB
`Qwen3-VL-2B-Instruct-heretic-Q4_0.gguf`	GGUF Q4_0	0.98 GB
`Qwen3-VL-2B-Instruct-heretic-Q4_1.gguf`	GGUF Q4_1	1.06 GB
`Qwen3-VL-2B-Instruct-heretic-Q4_K_M.gguf`	GGUF Q4_K_M	1.03 GB
`Qwen3-VL-2B-Instruct-heretic-Q5_K_S.gguf`	GGUF Q5_K_S	1.15 GB
`Qwen3-VL-2B-Instruct-heretic-Q5_K_M.gguf`	GGUF Q5_K_M	1.17 GB
`Qwen3-VL-2B-Instruct-heretic-Q6_K.gguf`	GGUF Q6_K	1.32 GB
`Qwen3-VL-2B-Instruct-heretic-Q8_0.gguf`	GGUF Q8_0	1.71 GB

Qwen3-VL architecture (qwen3vl) with its vision encoder - loads natively in llama.cpp / LM Studio / Jan.

Run llama serve -hf saidutta69/Qwen3-VL-2B-Instruct-heretic to pull the default quant.

Quickstart

# llama.cpp - the vision projector ships with the GGUF
llama serve -hf saidutta69/Qwen3-VL-2B-Instruct-heretic

# transformers
from transformers import AutoProcessor, AutoModelForImageTextToText

model_name = "saidutta69/Qwen3-VL-2B-Instruct-heretic"
model = AutoModelForImageTextToText.from_pretrained(model_name, dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained(model_name)

messages = [{"role": "user", "content": [
    {"type": "image", "image": "https://example.com/screenshot.png"},
    {"type": "text", "text": "Transcribe all text in this image and describe the layout."},
]}]
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=1024)
print(processor.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

Grounding and OCR

Qwen3-VL emits bounding boxes in a normalised coordinate space, so you can ask for element positions directly and get coordinates back rather than prose descriptions:

messages = [{"role": "user", "content": [
    {"type": "image", "image": "https://example.com/page.jpg"},
    {"type": "text", "text": "Give the bounding box of the submit button."},
]}]

This is the practical path for UI automation and for building training data from screenshots.

Model details


Architecture	`Qwen3VLForConditionalGeneration` (vision-language decoder)
Parameters	~2B
Layers / heads	28 layers, 16 attention heads, 8 KV heads, head dim 128
Hidden / intermediate	2048 / 6144
Position embedding	mRoPE (interleaved, sections 24/20/20), theta = 5,000,000
Context length	262,144
Vocab	151,936
Precision	bfloat16
Modalities	Text and image/video in, text out
Base model	Qwen/Qwen3-VL-2B-Instruct

About Qwen3-VL

Qwen3-VL is the vision-language branch of the Qwen series, available in dense and MoE sizes with Instruct and Thinking editions. This generation brings deeper visual perception and reasoning, extended context, stronger spatial and video understanding, and improved agent interaction — OCR, grounding, and video temporal reasoning are the headline capabilities over the earlier Qwen2.5-VL.

Responsible use

Refusal suppression is deliberate and works as intended: this model will comply with requests the base model would refuse, including some it shouldn't. There is no safety filtering layered on top. You are responsible for how you deploy it — don't put this behind an unmoderated public-facing endpoint serving third parties. It inherits Qwen3-VL's factual limitations and biases; abliteration removes refusal directions, it doesn't add capability or judgment.

License

Inherits the apache-2.0 license from the base model.

Qwen/Qwen3-VL-2B-Instruct — the base model
saidutta69/gemma-4-E4B-it-heretic — the larger multimodal sibling in this collection
RACER IS OP — Heretic Models — full collection

Downloads last month: 1,566

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for saidutta69/Qwen3-VL-2B-Instruct-heretic

Base model

Qwen/Qwen3-VL-2B-Instruct

Quantized

(99)

this model

Collection including saidutta69/Qwen3-VL-2B-Instruct-heretic

RACER IS OP — Heretic Models

Collection

All abliterated/heretic models by RACER IS OP — uncensored variants of open-weight LLMs • 57 items • Updated 1 day ago • 6

saidutta69
/

Qwen3-VL-2B-Instruct-heretic

Qwen3-VL-2B-Instruct-heretic

Runs on your gaming PC

Abliteration parameters

Performance

Why abliteration instead of fine-tuning

Files

Safetensors

GGUF quantizations

Quickstart

Grounding and OCR

Model details

About Qwen3-VL

Responsible use

License

Related

Model tree for saidutta69/Qwen3-VL-2B-Instruct-heretic

Collection including saidutta69/Qwen3-VL-2B-Instruct-heretic

RACER IS OP — Heretic Models