Instructions to use tanziro/qwen-bangla-crime-investigation-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tanziro/qwen-bangla-crime-investigation-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 tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tanziro/qwen-bangla-crime-investigation-gguf: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 tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tanziro/qwen-bangla-crime-investigation-gguf: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 tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M

Use Docker

docker model run hf.co/tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use tanziro/qwen-bangla-crime-investigation-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tanziro/qwen-bangla-crime-investigation-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": "tanziro/qwen-bangla-crime-investigation-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M

Ollama
How to use tanziro/qwen-bangla-crime-investigation-gguf with Ollama:
```
ollama run hf.co/tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M
```
Unsloth Desktop

How to use tanziro/qwen-bangla-crime-investigation-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tanziro/qwen-bangla-crime-investigation-gguf: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": "tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tanziro/qwen-bangla-crime-investigation-gguf with Docker Model Runner:
```
docker model run hf.co/tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M
```

Lemonade

How to use tanziro/qwen-bangla-crime-investigation-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M

Run and chat with the model

lemonade run user.qwen-bangla-crime-investigation-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use tanziro/qwen-bangla-crime-investigation-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 tanziro/qwen-bangla-crime-investigation-gguf: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 tanziro/qwen-bangla-crime-investigation-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tanziro/qwen-bangla-crime-investigation-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tanziro/qwen-bangla-crime-investigation-gguf: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 "tanziro/qwen-bangla-crime-investigation-gguf: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"

Qwen Bangla Crime Investigation GGUF

Status: merged GGUF verified and ready

This repository is intended to contain a standalone merged GGUF for LM Studio and other llama.cpp-compatible runtimes.

File

qwen-bangla-crime-investigation-Q4_K_M.gguf: standalone merged Q4_K_M GGUF for local inference.

Source

Base model: Qwen/Qwen3.5-9B
Merge base GGUF: jc-builds/Qwen3.5-9B-Q4_K_M-GGUF / Qwen3.5-9B-Q4_K_M.gguf
Source LoRA adapter: tanziro/qwen-bangla-crime-investigation-lora
Source LoRA adapter GGUF: tanziro/qwen-bangla-crime-investigation-lora-gguf / qwen-bangla-crime-investigation-lora.F16.gguf
Dataset: tanziro/bangla-crime-investigation-patterns-v2

LM Studio Use

Download qwen-bangla-crime-investigation-Q4_K_M.gguf in LM Studio as a local GGUF model. This repo is different from the LoRA-adapter GGUF repo: this file is merged and does not require loading a separate adapter.

Suggested system prompt:

You are a Bangladesh-focused crime investigation and investigative journalism assistant.
Answer with the final response only. Do not reveal hidden reasoning or step-by-step thinking.
Separate confirmed facts, source claims, and inference.
Do not identify private people from anonymized records.
Avoid doxxing, harassment, vigilantism, or instructions that enable crime or evidence tampering.
Recommend lawful, ethical next steps: document review, source corroboration, official records, expert consultation, right of reply, and personal safety.

Training Notes

The source adapter training run completed 747 of 1200 planned optimizer steps. Logged validation loss was best at step 300 (0.389918), while training loss continued to improve through step 700.

Step	Training Loss	Validation Loss
100	0.385574	0.409264
200	0.354652	0.394317
300	0.356278	0.389918
400	0.350144	0.391207
500	0.335047	0.391896
600	0.318425	0.399930
700	0.294148	0.406011

Known Limitation

The source adapter sometimes emits verbose reasoning traces such as Thinking Process. Use a system prompt that asks for final answers only. Future fine-tuning should include answer-only examples to suppress chain-of-thought style output.

Responsible Use

This model is not a law-enforcement system, legal advisor, or substitute for editorial review. Treat outputs as drafting assistance only. Verify high-stakes claims with documents, official records, independent sources, expert review, and right of reply before publication or action.

Build Provenance

Build notebook stage: merged GGUF verified and ready
Last updated: 2026-05-26 23:49:49 UTC
Merge method: llama-export-lora from a Q4_K_M base GGUF, then llama-quantize --allow-requantize Q4_K_M.

Downloads last month: 22

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for tanziro/qwen-bangla-crime-investigation-gguf

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(493)

this model

tanziro
/

qwen-bangla-crime-investigation-gguf

Qwen Bangla Crime Investigation GGUF

File

Source

LM Studio Use

Training Notes

Known Limitation

Responsible Use

Build Provenance

Model tree for tanziro/qwen-bangla-crime-investigation-gguf

Dataset used to train tanziro/qwen-bangla-crime-investigation-gguf