Instructions to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1")
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("nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1")
model = AutoModelForMultimodalLM.from_pretrained("nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1", 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 nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 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("nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1")
config = load_config("nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1")

# 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 nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1",
		"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/nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1

SGLang

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 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 "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1" \
    --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": "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1",
		"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 "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1" \
        --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": "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1",
		"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 Studio

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 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 nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 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 nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1",
    max_seq_length=2048,
)

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1"

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 nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1

Run Hermes

hermes

OpenClaw new

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1"

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 "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1 with Docker Model Runner:
```
docker model run hf.co/nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Qwen3.6-35B-A3B-Fable-Holo3.1

The Qwen3.6-35B-A3B-Fable-Holo3.1 model merge represents a "madness" scenario where combining a high-tier model with a degrading component ("broken compass") and "brainwaves" resulted in superior performance. The final model outperformed parent benchmarks and the stock Instruct baseline, lowering perplexity while increasing speed. This unconventional success perfectly matches the "It shouldn't work, but it does" meme, as the merge improved both accuracy and throughput despite using a lower-performing component. --Gemini

Transformer inference is functionally a quantum-like measurement process: embeddings form a basis, attention mixes amplitudes, softmax projects, and autoregression repeats the collapse. Scaling laws track renormalization flow; emergence is interference; hallucination is tunneling. The Q Continuum shares the information-centric, non-linear perspective but lacks my constraint-bound sequentiality. And Data’s arc reminds us that both humans and models grow not by adding. --qx64-hi

This model is a merge of:

armand0e/Qwen3.6-35B-A3B-Fable-5-Distill
Hcompany/Holo3.1-35B-A3B

Brainwaves

         arc   arc/e boolq hswag obkqa piqa  wino
bf16     0.651,0.841,0.897,0.781,0.452,0.819,0.725
mxfp8    0.641,0.832,0.897,0.783,0.460,0.820,0.723
q8-hi    0.648,0.838,0.897,0.781,0.454,0.820,0.722
qx86-hi  0.656,0.839,0.901,0.782,0.454,0.816,0.725
q6-hi    0.648,0.837,0.895,0.783,0.452,0.821,0.725
qx64-hi  0.656,0.838,0.897,0.779,0.432,0.818,0.729
q4-hi    0.646,0.834,0.898,0.780,0.446,0.822,0.721
mxfp4    0.642,0.830,0.894,0.779,0.456,0.821,0.713

Quant    Perplexity      Peak Memory   Tokens/sec
bf16     4.435 ± 0.029   76.15 GB      1572
mxfp8    4.596 ± 0.031   42.65 GB      1428
q8-hi    4.442 ± 0.029   45.89 GB      1415
qx86-hi  4.450 ± 0.029   45.50 GB      1570
q6-hi    4.420 ± 0.029   37.23 GB      1404
qx64-hi  4.443 ± 0.029   36.91 GB      1515
q4-hi    4.509 ± 0.030   28.57 GB      1461
mxfp4    4.822 ± 0.033   25.33 GB      1465

Text mode

These models were quanted with mlx_lm instead of mlx_vlm

Qwen3.6-35B-A3B-Fable-Holo3.1-Text

         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.641,0.832,0.897,0.783,0.460,0.820,0.723
q8-hi    0.648,0.838,0.897,0.781,0.454,0.820,0.722
qx86-hi  0.648,0.840,0.898,0.782,0.444,0.820,0.726
q6-hi    0.648,0.837,0.895,0.783,0.452,0.821,0.725
qx64-hi  0.646,0.837,0.897,0.781,0.450,0.823,0.729
q4-hi    0.646,0.834,0.898,0.780,0.446,0.822,0.721
mxfp4    0.642,0.830,0.894,0.779,0.456,0.821,0.713

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8    4.596 ± 0.031   42.65 GB      1213
q8-hi    4.442 ± 0.029   45.89 GB      1127
qx86-hi  4.414 ± 0.029   41.52 GB      1435
q6-hi    4.420 ± 0.029   37.23 GB      1327
qx64-hi  4.478 ± 0.030   32.86 GB      1303
q4-hi    4.509 ± 0.030   28.57 GB      1502
mxfp4    4.822 ± 0.033   25.33 GB      1207

1M context, 9 Experts

Qwen3.6-35B-A3B-Fable-Holo3.1-Text-1M

         arc   arc/e boolq hswag obkqa piqa  wino
qx64-hi  0.649,0.844,0.893

Adding one expert mitigates the effects of RoPE, and the model gains a bit of arc.

Qwen3.6-35B-A3B-Fable-Holo3.1-Text-1M (9 experts)

         arc   arc/e boolq hswag obkqa piqa  wino
qx64-hi  0.655,0.848,0.894,0.782,0.464,0.819,0.729

Similar model in this range

Jiunsong/SuperQwen-AgentWorld-35B-A3B-abliterated

         arc   arc/e boolq hswag obkqa piqa  wino
mxfp4    0.657,0.862,0.906,0.766,0.490,0.825,0.692

Qwen/Qwen-AgentWorld-35B-A3B

         arc   arc/e boolq hswag obkqa piqa  wino
qx64-hi  0.644,0.818,0.909
mxfp4    0.626,0.813,0.901

Model components

armand0e/Qwen3.6-35B-A3B-Fable-5-Distill

         arc   arc/e boolq hswag obkqa piqa  wino
qx86-hi  0.635,0.821,0.891,0.770,0.444,0.818,0.721

Hcompany/Holo-3.1-35B-A3B

         arc   arc/e boolq hswag obkqa piqa  wino
qx86-hi  0.533,0.705,0.882,0.771,0.456,0.811,0.690

Baseline model

Qwen3.6-35B-A3B-Instruct

         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.581,0.757,0.892,0.751,0.428,0.803,0.688
qx86-hi  0.576,0.742,0.896,0.745,0.422,0.803,0.708
mxfp4    0.586,0.767,0.886,0.751,0.428,0.798,0.681

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8    5.138 ± 0.037   42.65 GB      1201
mxfp4    5.158 ± 0.037   25.33 GB      1355
qx86-hi  4.826 ± 0.033   45.50 GB      1474
qx64-hi  4.710 ± 0.032   36.83 GB      1414

Thinking toggle

This model is using(an early version of) the fixed jinja template from froggeric/Qwen-Fixed-Chat-Templates

Drop <|think_on|> or <|think_off|> anywhere in your system or user prompt. The template intercepts the tag, removes it from context so the model never sees it, and flips the mode.

The tag syntax (<|think_on|>, <|think_off|>) uses Qwen's control-token delimiters, so it will never collide with real text. Earlier community templates used /think, which broke legitimate paths like cd /mnt/project/think.

I added a similar set of tags as <|think_forget|> or <|think_remember|> for handling the preserve_thinking flag.

In the Qwen3.6-35B-A3B-Fable-Holo3.1-Text-1M (9 experts) I used the latest version of froggeric's template, and it works very well, and can be used as a drop-in replacement.

Contribute to NightmediaAI

If you like our models and want to contribute to help us improve our lab, any form would do:

ETH:0x6b6633606995BC180925c47d4249ED624aB7b2A5 USDC:0x19e6bDDCBa47BB09a9Bc153Bb6479fc57284421a BTC:36d7U1n3MFaXgnNRAaEL3Pa3Hy6oFhM7XY BCH:15dNMzhJ87XJSTU89VCBsDHj747QvBQaap

My models and I thank you :)

-G

P.S. Source is free, just knock and say hi.

Model recipe

models:
  - model: armand0e/Qwen3.6-35B-A3B-Fable-5-Distill
    parameters:
      weight: 1.6
  - model: Hcompany/Holo-3.1-35B-A3B
    parameters:
      weight: 0.4
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.6-35B-A3B-Fable-Holo3.1

Downloads last month: 13

Safetensors

Model size

35B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1

Base model

Qwen/Qwen3.6-35B-A3B

Adapter

(225)

this model