Instructions to use TigerKay/qwen35-sft-v2-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TigerKay/qwen35-sft-v2-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TigerKay/qwen35-sft-v2-gguf",
	filename="qwen35-sft-v2-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TigerKay/qwen35-sft-v2-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TigerKay/qwen35-sft-v2-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TigerKay/qwen35-sft-v2-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TigerKay/qwen35-sft-v2-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TigerKay/qwen35-sft-v2-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 TigerKay/qwen35-sft-v2-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TigerKay/qwen35-sft-v2-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 TigerKay/qwen35-sft-v2-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TigerKay/qwen35-sft-v2-gguf:Q4_K_M

Use Docker

docker model run hf.co/TigerKay/qwen35-sft-v2-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use TigerKay/qwen35-sft-v2-gguf with Ollama:
```
ollama run hf.co/TigerKay/qwen35-sft-v2-gguf:Q4_K_M
```

Unsloth Studio new

How to use TigerKay/qwen35-sft-v2-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 TigerKay/qwen35-sft-v2-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 TigerKay/qwen35-sft-v2-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TigerKay/qwen35-sft-v2-gguf to start chatting

Pi new

How to use TigerKay/qwen35-sft-v2-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf TigerKay/qwen35-sft-v2-gguf:Q4_K_M

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": "TigerKay/qwen35-sft-v2-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use TigerKay/qwen35-sft-v2-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 TigerKay/qwen35-sft-v2-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 TigerKay/qwen35-sft-v2-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use TigerKay/qwen35-sft-v2-gguf with Docker Model Runner:
```
docker model run hf.co/TigerKay/qwen35-sft-v2-gguf:Q4_K_M
```

Lemonade

How to use TigerKay/qwen35-sft-v2-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TigerKay/qwen35-sft-v2-gguf:Q4_K_M

Run and chat with the model

lemonade run user.qwen35-sft-v2-gguf-Q4_K_M

List all available models

lemonade list

Qwen3.5-35B-A3B — Verbose Image Captioning (SFT v2)

Fine-tuned Qwen3.5-35B-A3B for detailed image captioning with structured XML spatial reasoning.

What it does

Given an image, the model generates:

A <think> block with XML spatial analysis (<visual_parsing_graph>) covering scene composition, entity mapping, interactions, and lighting
A detailed flowing prose description

The XML reasoning acts as chain-of-thought, grounding the prose in what the model actually observes.

Files

File	Size	Description
`qwen35-sft-v2-f16.gguf`	65 GB	Full precision (f16)
`qwen35-sft-v2-Q4_K_M.gguf`	20 GB	Quantized (Q4_K_M, 4.88 BPW)
`qwen35-sft-v2-mmproj-f16.gguf`	858 MB	Vision projector (required)

Usage (llama.cpp)

llama-mtmd-cli \
  -m qwen35-sft-v2-Q4_K_M.gguf \
  --mmproj qwen35-sft-v2-mmproj-f16.gguf \
  -p "Describe this image in extremely high detail. Include a structured spatial analysis as XML followed by a flowing prose description." \
  --image your_image.jpg \
  -ngl 99 -n 2048 --repeat-penalty 1.15

Note: --repeat-penalty 1.15 is recommended to prevent tag repetition loops in the XML output.

Training details

Base model: Qwen3.5-35B-A3B (MoE, 35B total / 3B active)
Method: LoRA (r=32, alpha=32) via Unsloth
Trainable params: 1.9B / 37B (5.15%)
Dataset: ~8.9k image-caption pairs with XML spatial analysis + prose
Epochs: 2
Final loss: 0.719
Precision: bf16
Hardware: NVIDIA H200 (141 GB)
Training time: ~2 hours

Prompt format

The model responds best to this specific instruction:

Describe this image in extremely high detail. Include a structured spatial analysis as XML followed by a flowing prose description.

Other prompts will still produce captions, but without the XML structure.

Limitations

Tag repetition loops can occur without repeat penalty — use --repeat-penalty 1.15
May occasionally hallucinate character names or minor color details
Optimized for furry/anthro art — performance on other domains not tested

Downloads last month: 20

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TigerKay/qwen35-sft-v2-gguf

Base model

Qwen/Qwen3.5-35B-A3B-Base

Finetuned

Qwen/Qwen3.5-35B-A3B

Adapter

(26)

this model