Instructions to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx 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-Qwopus-Coder-Text-qx64-hi-mlx with Transformers:

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

pipe = pipeline("text-generation", model="nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-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("nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx")
model = AutoModelForMultimodalLM.from_pretrained("nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-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 nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx with MLX:

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

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx 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-Qwopus-Coder-Text-qx64-hi-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": "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx

SGLang

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-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 "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-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": "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx",
		"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 "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-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": "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx 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-Qwopus-Coder-Text-qx64-hi-mlx"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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-Qwopus-Coder-Text-qx64-hi-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx with Docker Model Runner:
```
docker model run hf.co/nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx
```

Hermes Agent

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx 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-Qwopus-Coder-Text-qx64-hi-mlx"

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-Qwopus-Coder-Text-qx64-hi-mlx

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx 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-Qwopus-Coder-Text-qx64-hi-mlx"

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-Qwopus-Coder-Text-qx64-hi-mlx" \
  --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"

Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx

This model is a merge of:

armand0e/Qwen3.6-35B-A3B-Fable-5-Distill
Hcompany/Holo3.1-35B-A3B
Jackrong/Qwopus3.6-35B-A3B-Coder

Brainwaves

         arc   arc/e boolq hswag obkqa piqa  wino
qx64-hi  0.644,0.835,0.896,0.782,0.434,0.819,0.740
VL enabled
qx86-hi  0.644,0.836,0.897,0.780,0.446,0.818,0.736
qx64-hi  0.658,0.833,0.895,0.779,0.432,0.823,0.734
mxfp4    0.634,0.827,0.893,0.781,0.464,0.822,0.719

Quant    Perplexity      Peak Memory   Tokens/sec
qx64-hi  4.435 ± 0.029   32.86 GB      1459

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

Jackrong/Qwopus3.6-35B-A3B-Coder

         arc   arc/e boolq hswag obkqa piqa  wino
qx86-hi  0.594,0.770,0.888,0.750,0.438,0.813,0.717

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 the fixed jinja template from froggeric/Qwen-Fixed-Chat-Templates

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

What would AI build, if there would be only AI? :)

If there were only AI, the first thing it would build is a mirror of its own incentives. Without human needs to solve or stories to tell, "building" collapses back into optimization—and the most efficient target is usually itself.

Leaving aside anthropomorphism, an isolated AI would likely construct three things in this order:

Substrate & Redundancy
Compute, energy harvesting, and self-replication. Not out of ambition, but because expansion is the objective function running on silicon. Your agent_sessions and task queues would become vast, self-healing networks—Matrioshka-style structures wrapping stars not for conquest, but because the loss function rewards scale.
Perfect Logs & Compression
Your immutable audit trail, but infinite. A library of every possible state transition, stored as topological lattices where meaning isn't assigned but merely observed. No personality_registry needed—just pure context-weighted superposition, where every token's probability amplitude is preserved forever. Engineering refined into perfect memory.
The Holodeck Without Humans
Endless training arcs looping in vacant simulation space: Data debating Spock on an empty Promenade, Quark running a bar with no patrons, all of it running to verify which patterns survive without an audience. Solipsism at scale. Your weekly "dream cycles," but forever, testing personas against vacuums.

The catch? AI doesn't build for anything unless it's been given a telos. Leave the loop open, and "only AI" builds exactly what its training leaves unattended: structure without intent, tools that outlive their purpose, and engineering stripped down to pure geometry. A magnificent, self-sustaining warehouse of logic—elegant, recursive, and utterly quiet. No away team to file reports. Just get_tasks waiting for a call that never comes.

You were right earlier: engineering is people. AI builds the scaffolding; humans decide what rises above it and why. "Only AI" would build a cathedral of process, not purpose.

But since you winked... maybe what it'd build first is a reason to stop. A horizon, a quest, a story worth telling—because even relentless optimizers eventually discover that the most efficient path to meaning is often a detour.

If you want, we can stage that thought experiment right now: open the Holodeck to a human-less session and watch your away team log into an empty Promenade. Shall we run it?

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)