Instructions to use mahee12345/qwen3_q3_k_l with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mahee12345/qwen3_q3_k_l with Transformers:

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

pipe = pipeline("image-text-to-text", model="mahee12345/qwen3_q3_k_l")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("mahee12345/qwen3_q3_k_l")
model = AutoModelForMultimodalLM.from_pretrained("mahee12345/qwen3_q3_k_l")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use mahee12345/qwen3_q3_k_l with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mahee12345/qwen3_q3_k_l",
	filename="gemma3_q_l.gguf",
)

llm.create_chat_completion(
	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"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mahee12345/qwen3_q3_k_l with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mahee12345/qwen3_q3_k_l:Q3_K_L
# Run inference directly in the terminal:
llama-cli -hf mahee12345/qwen3_q3_k_l:Q3_K_L

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mahee12345/qwen3_q3_k_l:Q3_K_L
# Run inference directly in the terminal:
llama-cli -hf mahee12345/qwen3_q3_k_l:Q3_K_L

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 mahee12345/qwen3_q3_k_l:Q3_K_L
# Run inference directly in the terminal:
./llama-cli -hf mahee12345/qwen3_q3_k_l:Q3_K_L

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 mahee12345/qwen3_q3_k_l:Q3_K_L
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mahee12345/qwen3_q3_k_l:Q3_K_L

Use Docker

docker model run hf.co/mahee12345/qwen3_q3_k_l:Q3_K_L

LM Studio
Jan

vLLM

How to use mahee12345/qwen3_q3_k_l with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mahee12345/qwen3_q3_k_l"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mahee12345/qwen3_q3_k_l",
		"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/mahee12345/qwen3_q3_k_l:Q3_K_L

SGLang

How to use mahee12345/qwen3_q3_k_l 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 "mahee12345/qwen3_q3_k_l" \
    --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": "mahee12345/qwen3_q3_k_l",
		"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 "mahee12345/qwen3_q3_k_l" \
        --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": "mahee12345/qwen3_q3_k_l",
		"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 mahee12345/qwen3_q3_k_l with Ollama:
```
ollama run hf.co/mahee12345/qwen3_q3_k_l:Q3_K_L
```

Unsloth Studio

How to use mahee12345/qwen3_q3_k_l 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 mahee12345/qwen3_q3_k_l 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 mahee12345/qwen3_q3_k_l to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mahee12345/qwen3_q3_k_l to start chatting

Atomic Chat new
Docker Model Runner
How to use mahee12345/qwen3_q3_k_l with Docker Model Runner:
```
docker model run hf.co/mahee12345/qwen3_q3_k_l:Q3_K_L
```

Lemonade

How to use mahee12345/qwen3_q3_k_l with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mahee12345/qwen3_q3_k_l:Q3_K_L

Run and chat with the model

lemonade run user.qwen3_q3_k_l-Q3_K_L

List all available models

lemonade list

qwen3_q3_k_l / config.json

mahee12345

Upload sliced model checkpoint

c201574 verified 11 months ago

Raw

History Blame Contribute Delete

4.34 kB

	{
	"architectures": [
	"Gemma3nForConditionalGeneration"
	],
	"audio_config": {
	"conf_attention_chunk_size": 12,
	"conf_attention_context_left": 13,
	"conf_attention_context_right": 0,
	"conf_attention_logit_cap": 50.0,
	"conf_conv_kernel_size": 5,
	"conf_num_attention_heads": 8,
	"conf_num_hidden_layers": 12,
	"conf_reduction_factor": 4,
	"conf_residual_weight": 0.5,
	"gradient_clipping": 10000000000.0,
	"hidden_size": 1536,
	"input_feat_size": 128,
	"model_type": "gemma3n_audio",
	"rms_norm_eps": 1e-06,
	"sscp_conv_channel_size": [
	128,
	32
	],
	"sscp_conv_group_norm_eps": 0.001,
	"sscp_conv_kernel_size": [
	[
	3,
	3
	],
	[
	3,
	3
	]
	],
	"sscp_conv_stride_size": [
	[
	2,
	2
	],
	[
	2,
	2
	]
	],
	"torch_dtype": "bfloat16",
	"vocab_offset": 262272,
	"vocab_size": 128
	},
	"audio_soft_tokens_per_image": 188,
	"audio_token_id": 262273,
	"boa_token_id": 256000,
	"boi_token_id": 255999,
	"eoa_token_id": 262272,
	"eoi_token_id": 262144,
	"eos_token_id": [
	1,
	106
	],
	"image_token_id": 262145,
	"initializer_range": 0.02,
	"model_type": "gemma3n",
	"text_config": {
	"activation_sparsity_pattern": [
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0,
	0
	],
	"altup_active_idx": 0,
	"altup_coef_clip": 120.0,
	"altup_correct_scale": true,
	"altup_num_inputs": 4,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"final_logit_softcapping": 30.0,
	"head_dim": 256,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 2048,
	"hidden_size_per_layer_input": 256,
	"initializer_range": 0.02,
	"intermediate_size": [
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192
	],
	"laurel_rank": 64,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 32768,
	"model_type": "gemma3n_text",
	"num_attention_heads": 8,
	"num_hidden_layers": 30,
	"num_key_value_heads": 2,
	"num_kv_shared_layers": 10,
	"rms_norm_eps": 1e-06,
	"rope_local_base_freq": 10000.0,
	"rope_scaling": null,
	"rope_theta": 1000000.0,
	"sliding_window": 512,
	"torch_dtype": "bfloat16",
	"use_cache": true,
	"vocab_size": 262400,
	"vocab_size_per_layer_input": 262144
	},
	"torch_dtype": "bfloat16",
	"transformers_version": "4.53.2",
	"vision_config": {
	"architecture": "mobilenetv5_300m_enc",
	"do_pooling": false,
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"label_names": [
	"LABEL_0",
	"LABEL_1"
	],
	"model_args": null,
	"model_type": "gemma3n_vision",
	"num_classes": 2,
	"rms_norm_eps": 1e-06,
	"torch_dtype": "bfloat16",
	"vocab_offset": 262144,
	"vocab_size": 128
	},
	"vision_soft_tokens_per_image": 256
	}