Instructions to use alibayram/magibu-11b-v8-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alibayram/magibu-11b-v8-mlx with Transformers:

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

pipe = pipeline("image-text-to-text", model="alibayram/magibu-11b-v8-mlx")
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("alibayram/magibu-11b-v8-mlx")
model = AutoModelForMultimodalLM.from_pretrained("alibayram/magibu-11b-v8-mlx", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use alibayram/magibu-11b-v8-mlx with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("alibayram/magibu-11b-v8-mlx")
config = load_config("alibayram/magibu-11b-v8-mlx")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use alibayram/magibu-11b-v8-mlx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alibayram/magibu-11b-v8-mlx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alibayram/magibu-11b-v8-mlx",
		"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/alibayram/magibu-11b-v8-mlx

SGLang

How to use alibayram/magibu-11b-v8-mlx 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 "alibayram/magibu-11b-v8-mlx" \
    --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": "alibayram/magibu-11b-v8-mlx",
		"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 "alibayram/magibu-11b-v8-mlx" \
        --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": "alibayram/magibu-11b-v8-mlx",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use alibayram/magibu-11b-v8-mlx with Docker Model Runner:
```
docker model run hf.co/alibayram/magibu-11b-v8-mlx
```
Atomic Chat

alibayram commited on Feb 16

Commit

df2f7b8

verified ·

1 Parent(s): c7f4c1b

Update config.json

Browse files

Files changed (1) hide show

config.json +121 -122

config.json CHANGED Viewed

@@ -1,126 +1,125 @@
 {
-    "architectures": [
-        "Gemma3ForConditionalGeneration"
-    ],
-    "boi_token_index": 3,
-    "bos_token_id": 2,
     "dtype": "bfloat16",
-    "eoi_token_index": 130971,
-    "eos_token_id": [
-        1,
-        1,
-        106
-    ],
-    "image_token_index": 131072,
     "initializer_range": 0.02,
-    "mm_tokens_per_image": 256,
-    "model_type": "gemma3",
-    "pad_token_id": 0,
-    "quantization": {
-        "group_size": 64,
-        "bits": 4,
-        "mode": "affine"
-    },
-    "quantization_config": {
-        "group_size": 64,
-        "bits": 4,
-        "mode": "affine"
-    },
-    "text_config": {
-        "_sliding_window_pattern": 6,
-        "attention_bias": false,
-        "attention_dropout": 0.0,
-        "attn_logit_softcapping": null,
-        "dtype": "bfloat16",
-        "final_logit_softcapping": null,
-        "head_dim": 256,
-        "hidden_activation": "gelu_pytorch_tanh",
-        "hidden_size": 3840,
-        "initializer_range": 0.02,
-        "intermediate_size": 15360,
-        "layer_types": [
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "full_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "full_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "full_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "full_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "full_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "full_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "full_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "sliding_attention",
-            "full_attention"
-        ],
-        "max_position_embeddings": 131072,
-        "model_type": "gemma3_text",
-        "num_attention_heads": 16,
-        "num_hidden_layers": 48,
-        "num_key_value_heads": 8,
-        "query_pre_attn_scalar": 256,
-        "rms_norm_eps": 1e-06,
-        "rope_local_base_freq": 10000.0,
-        "rope_scaling": {
-            "factor": 8.0,
-            "rope_type": "linear"
-        },
-        "rope_theta": 1000000.0,
-        "sliding_window": 1024,
-        "use_bidirectional_attention": false,
-        "use_cache": true,
-        "vocab_size": 131136
     },
-    "transformers_version": "4.57.6",
-    "unsloth_version": "2026.2.1",
-    "vision_config": {
-        "attention_dropout": 0.0,
-        "dtype": "bfloat16",
-        "hidden_act": "gelu_pytorch_tanh",
-        "hidden_size": 1152,
-        "image_size": 896,
-        "intermediate_size": 4304,
-        "layer_norm_eps": 1e-06,
-        "model_type": "siglip_vision_model",
-        "num_attention_heads": 16,
-        "num_channels": 3,
-        "num_hidden_layers": 27,
-        "patch_size": 14,
-        "vision_use_head": false
-    }
-}

 {
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 3,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eoi_token_index": 130971,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 131072,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "pad_token_id": 0,
+  "quantization": {
+    "group_size": 64,
+    "bits": 4,
+    "mode": "affine"
+  },
+  "quantization_config": {
+    "group_size": 64,
+    "bits": 4,
+    "mode": "affine"
+  },
+  "text_config": {
+    "_sliding_window_pattern": 6,
+    "attention_bias": false,
+    "attention_dropout": 0,
+    "attn_logit_softcapping": null,
     "dtype": "bfloat16",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
     "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 0.000001,
+    "rope_local_base_freq": 10000,
+    "rope_scaling": {
+      "factor": 8,
+      "rope_type": "linear"
     },
+    "rope_theta": 1000000,
+    "sliding_window": 1024,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 131136
+  },
+  "transformers_version": "4.57.6",
+  "unsloth_version": "2026.2.1",
+  "vision_config": {
+    "attention_dropout": 0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 0.000001,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}