Instructions to use Chun121/qwen3-4B-rpg-roleplay with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Chun121/qwen3-4B-rpg-roleplay with Transformers:

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

pipe = pipeline("text-generation", model="Chun121/qwen3-4B-rpg-roleplay")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Chun121/qwen3-4B-rpg-roleplay", dtype="auto")

llama-cpp-python

How to use Chun121/qwen3-4B-rpg-roleplay with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Chun121/qwen3-4B-rpg-roleplay",
	filename="gguf_f16/unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Chun121/qwen3-4B-rpg-roleplay with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Chun121/qwen3-4B-rpg-roleplay: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 Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Chun121/qwen3-4B-rpg-roleplay: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 Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

Use Docker

docker model run hf.co/Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

LM Studio
Jan

vLLM

How to use Chun121/qwen3-4B-rpg-roleplay with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Chun121/qwen3-4B-rpg-roleplay"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Chun121/qwen3-4B-rpg-roleplay",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

SGLang

How to use Chun121/qwen3-4B-rpg-roleplay 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 "Chun121/qwen3-4B-rpg-roleplay" \
    --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": "Chun121/qwen3-4B-rpg-roleplay",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Chun121/qwen3-4B-rpg-roleplay" \
        --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": "Chun121/qwen3-4B-rpg-roleplay",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Chun121/qwen3-4B-rpg-roleplay with Ollama:
```
ollama run hf.co/Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
```

Unsloth Studio

How to use Chun121/qwen3-4B-rpg-roleplay 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 Chun121/qwen3-4B-rpg-roleplay 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 Chun121/qwen3-4B-rpg-roleplay to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Chun121/qwen3-4B-rpg-roleplay to start chatting

How to use Chun121/qwen3-4B-rpg-roleplay with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Chun121/qwen3-4B-rpg-roleplay: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": "Chun121/qwen3-4B-rpg-roleplay:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Chun121/qwen3-4B-rpg-roleplay with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Chun121/qwen3-4B-rpg-roleplay: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 Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Chun121/qwen3-4B-rpg-roleplay with Docker Model Runner:
```
docker model run hf.co/Chun121/qwen3-4B-rpg-roleplay:Q4_K_M
```

Lemonade

How to use Chun121/qwen3-4B-rpg-roleplay with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Chun121/qwen3-4B-rpg-roleplay:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-4B-rpg-roleplay-Q4_K_M

List all available models

lemonade list

How to Import Models into Ollama

by jier - opened Jun 4, 2025

Discussion

jier

Jun 4, 2025

I want to import a GGUF model into Ollama. How should I write the Modelfile?

jier

Jun 4, 2025

I'm using ollama run hf.co/Chun121/qwen3-4B-rpg-roleplay:Q4_K_M, but it's not running correctly. Could you provide a more detailed usage guide?

print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
llama_model_load: error loading model: missing tensor 'blk.0.attn_k_norm.weight'
llama_model_load_from_file_impl: failed to load model
⠏ panic: unable to load model: /root/.ollama/models/blobs/sha256-41a09afb836d2b5ab96d3e56197d11deabfe3b6f2b79d313687af4a4c4afd43e

goroutine 162 [running]:
github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc00063c000, {0x25, 0x0, 0x1, {0x0, 0x0, 0x0}, 0xc00061a220, 0x0}, {0x7fff2236a10a, ...}, ...)
github.com/ollama/ollama/runner/llamarunner/runner.go:751 +0x395
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
github.com/ollama/ollama/runner/llamarunner/runner.go:848 +0xb57
⠋ time=2025-06-04T14:16:29.413+08:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding"
time=2025-06-04T14:16:29.415+08:00 level=ERROR source=server.go:457 msg="llama runner terminated" error="exit status 2"
⠸ time=2025-06-04T14:16:29.664+08:00 level=ERROR source=sched.go:489 msg="error loading llama server" error="llama runner process has terminated: error loading model: missing tensor 'blk.0.attn_k_norm.weight'\nllama_model_load_from_file_impl: failed to load model"
[GIN] 2025/06/04 - 14:16:29 | 500 | 2.428391592s | 127.0.0.1 | POST "/api/generate"
Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.attn_k_norm.weight'
llama_model_load_from_file_impl: failed to load model
root@autodl-container-b9b842b3fc-4445dc68:~/autodl-tmp# time=2025-06-04T14:16:34.757+08:00 level=WARN source=sched.go:687 msg="gpu VRAM usage didn't recover within timeout" seconds=5.09328595 runner.size="4.7 GiB" runner.vram="4.7 GiB" runner.parallel=2 runner.pid=26130 runner.model=/root/.ollama/models/blobs/sha256-41a09afb836d2b5ab96d3e56197d11deabfe3b6f2b79d313687af4a4c4afd43e
time=2025-06-04T14:16:35.054+08:00 level=WARN source=sched.go:687 msg="gpu VRAM usage didn't recover within timeout" seconds=5.390141856 runner.size="4.7 GiB" runner.vram="4.7 GiB" runner.parallel=2 runner.pid=26130 runner.model=/root/.ollama/models/blobs/sha256-41a09afb836d2b5ab96d3e56197d11deabfe3b6f2b79d313687af4a4c4afd43e
time=2025-06-04T14:16:35.471+08:00 level=WARN source=sched.go:687 msg="gpu VRAM usage didn't recover within timeout" seconds=5.806662337 runner.size="4.7 GiB" runner.vram="4.7 GiB" runner.parallel=2 runner.pid=26130 runner.model=/root/.ollama/models/blobs/sha256-41a09afb836d2b5ab96d3e56197d11deabfe3b6f2b79d313687af4a4c4afd43e

Chun121

Owner Jun 4, 2025

you must first download the unsloth.Q4_K_M.gguf file locally, generate a base Modelfile template from the official qwen3:4b Modelfile, then edit it to reference the downloaded GGUF file. After creating the custom Modelfile, register the model with Ollama via ollama create and finally run it with ollama run. The error missing tensor 'blk.0.attn_k_norm.weight' indicates that Ollama could not locate the correct GGUF file or that the FROM path in the Modelfile was incorrect.

use command:
ollama show --modelfile qwen3:4b > Modelfile

it should give a file like:
FROM qwen3:4b
PARAMETER ...
TEMPLATE """
...
"""
SYSTEM """
...
"""

change the path/FROM line and template as necessary, here is example:

FROM ./unsloth.Q4_K_M.gguf
PARAMETER temperature 0.7
PARAMETER stop "<|im_start|>"
PARAMETER stop "<|im_end|>"
TEMPLATE """
<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""
SYSTEM """You are a helpful assistant."""

finally check it:
ollama list

and run:
ollama run chun/qwen3-4b-rpg:Q4_K_M

Hope it helps :)

Chun121

Owner Jun 4, 2025

for absolute model path add FROM like this:

FROM /home/username/models/qwen3-4B-rpg/unsloth.Q4_K_M.gguf

jier

Jun 4, 2025

for absolute model path add FROM like this:

FROM /home/username/models/qwen3-4B-rpg/unsloth.Q4_K_M.gguf

Thank you for your help. Can I run it on a Mac computer?

Chun121

Owner Jun 4, 2025

for absolute model path add FROM like this:

FROM /home/username/models/qwen3-4B-rpg/unsloth.Q4_K_M.gguf

Thank you for your help. Can I run it on a Mac computer?

yep pretty sure ollama have same behaviour on all platforms~

jier

Jun 4, 2025

for absolute model path add FROM like this:

FROM /home/username/models/qwen3-4B-rpg/unsloth.Q4_K_M.gguf

Thank you for your help. Can I run it on a Mac computer?

yep pretty sure ollama have same behaviour on all platforms~

Thank you for you reply, I used the ollama run command and got an error:
Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.attn_k_norm.weight'. can use other ways?

Chun121

Owner Jun 4, 2025

for absolute model path add FROM like this:

FROM /home/username/models/qwen3-4B-rpg/unsloth.Q4_K_M.gguf

Thank you for your help. Can I run it on a Mac computer?

yep pretty sure ollama have same behaviour on all platforms~

Thank you for you reply, I used the ollama run command and got an error:
Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.attn_k_norm.weight'. can use other ways?

that's weird, make sure the path is correct in modelfile and you run,

ollama create chun/qwen3-4b-rpg:Q4_K_M -f Modelfile

also make sure ollama is latest version, older versions can't run qwen 3 models.

jier

Jun 5, 2025

for absolute model path add FROM like this:

FROM /home/username/models/qwen3-4B-rpg/unsloth.Q4_K_M.gguf

Thank you for your help. Can I run it on a Mac computer?

yep pretty sure ollama have same behaviour on all platforms~

Thank you for you reply, I used the ollama run command and got an error:
Error: llama runner process has terminated: error loading model: missing tensor 'blk.0.attn_k_norm.weight'. can use other ways?

that's weird, make sure the path is correct in modelfile and you run,

ollama create chun/qwen3-4b-rpg:Q4_K_M -f Modelfile

also make sure ollama is latest version, older versions can't run qwen 3 models.

I'm about to break down. Even after I changed the 'From' field in the Modelfile to an absolute path, I still got the same error. I tried running qwen3, and it worked fine.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment