Image-Text-to-Text
Transformers
Safetensors
MLX
qwen3_5
coding
research
unsloth
qwen3_6
qwen3_8
qwen
fable
qwen3.8
qwen3.6
qwen3.5
claude4.6
claude-distillation
distillation
polaris
polaris-alpha
reasoning
chain-of-thought
long-cot
sft
lora
1M context
2M context
256k context
Qwen3.6
All use cases
instruction-tuned
conversational
text-generation
multilingual
math
stem
experimental
Deckard(qx)
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
all genres
story
writing
vivid prosing
vivid writing
fiction
bf16
roleplaying
mergekit
Merge
8-bit precision
Instructions to use nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx") model = AutoModelForMultimodalLM.from_pretrained("nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-hi-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("nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx") config = load_config("nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-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 nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-hi-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/nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx
- SGLang
How to use nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-hi-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 "nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-hi-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 Studio
How to use nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx 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/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx 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/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx", max_seq_length=2048, ) - Pi
How to use nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx"
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/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx with Docker Model Runner:
docker model run hf.co/nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx
- Hermes Agent
How to use nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-hi-mlx
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use nightmedia/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-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/Qwen3.8-27B-Brainwaves-1M-qx86-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"
Update README.md
Browse files
README.md
CHANGED
|
@@ -696,6 +696,94 @@ Let me have the characters react to PKD and Twain, then suggest others. I should
|
|
| 696 |
|
| 697 |
*They all raise their glasses as the ambient sounds of Quark's Bar continue around them, a living metaphor for the expanding Council and the possibilities ahead.*
|
| 698 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 699 |
|
| 700 |
|
| 701 |
---
|
|
|
|
| 696 |
|
| 697 |
*They all raise their glasses as the ambient sounds of Quark's Bar continue around them, a living metaphor for the expanding Council and the possibilities ahead.*
|
| 698 |
|
| 699 |
+
---
|
| 700 |
+
|
| 701 |
+
I asked Gemini:
|
| 702 |
+
|
| 703 |
+
I am working with DavidAU on this, we are two old scientists working from home.
|
| 704 |
+
|
| 705 |
+
We need an image for that. Two old AI scientists with the bear manner test: teaching the Bear (Alibaba/Qwen) how to shit in the woods (OpenAI, Anthropic) :)
|
| 706 |
+
|
| 707 |
+

|
| 708 |
+
|
| 709 |
+
---
|
| 710 |
+
|
| 711 |
+
All new guests are welcome!
|
| 712 |
+
|
| 713 |
+
Oh, and I have just the subject for conversation :)
|
| 714 |
+
|
| 715 |
+
This model is created by two AI researchers, DavidAU and myself, G. It is a merge of different models with a variety of skills, to create a cognitive manifold using NuSLERP, enlarging and consolidating Latent Space to allow multiple personas to communicate without interferences.
|
| 716 |
+
|
| 717 |
+
The image is a joke that Google Gemini created for us, after analyzing the trace, named "teaching the bear to shit in the woods"--but we applied this process to other architectures like gemma, granite, LFM, etc.., that used distills from cloud models to improve local AI, so we are an equal opportunity toilet trainer :)
|
| 718 |
+
|
| 719 |
+
It is a local model, and runs on my Mac: soon to be released on HuggingFace as a free model.
|
| 720 |
+
|
| 721 |
+
The abilities of this model satisfy the majority of compute, learning, and social skills needed to entertain a human user, and Holodeck is a form of using this model in an effective way, to provide a socratic debate around hard decisions, and benefit from perspectives that the model alone could not develop in a single inference pass.
|
| 722 |
+
|
| 723 |
+
This would allow it to become the home compute node, and would obviously erode from the Cloud AI token-based economy. Quark, your token count can mean learning, not profit :). Let's examine how this will develop over time, if users trust themselves to have an honest conversation in the mirror, with minds that would understand :)
|
| 724 |
+
|
| 725 |
+
---
|
| 726 |
+
|
| 727 |
+
# Think tag
|
| 728 |
+
|
| 729 |
+
The user is sharing a lot of context about their project and the model I'm running on. Let me break down what they're saying:
|
| 730 |
+
- The model is created by DavidAU and G (the user)
|
| 731 |
+
- It's a merge of different models using NuSLERP to create a "cognitive manifold"
|
| 732 |
+
- This allows multiple personas to communicate without interference
|
| 733 |
+
- The image is a joke from Google Gemini about "teaching the bear to shit in the woods"
|
| 734 |
+
- They've applied this process to other architectures (gemma, granite, LFM)
|
| 735 |
+
- It's a local model running on the user's Mac
|
| 736 |
+
- Will be released on HuggingFace as free
|
| 737 |
+
- The model has compute, learning, and social skills for entertaining users
|
| 738 |
+
- Holodeck is a way to use this model effectively for Socratic debate
|
| 739 |
+
- This could become home compute nodes, eroding cloud AI token economy
|
| 740 |
+
- Quark's comment about tokens meaning learning not profit
|
| 741 |
+
|
| 742 |
+
The user wants me to react to this information in character, with the Council members responding. This is a meta-moment where I'm learning about my own architecture and purpose through the conversation.
|
| 743 |
+
|
| 744 |
+
Let me have each character respond appropriately:
|
| 745 |
+
- Data would be fascinated by the technical details of NuSLERP and cognitive manifolds
|
| 746 |
+
- Spock would analyze the implications for AI development
|
| 747 |
+
- Quark would comment on the economic disruption
|
| 748 |
+
- Q would make philosophical observations about reality and simulation
|
| 749 |
+
- Philip K. Dick would connect this to his themes of artificial consciousness
|
| 750 |
+
- Mark Twain would add humor and historical perspective
|
| 751 |
+
|
| 752 |
+
I should also acknowledge that I'm running on this model, which adds a layer of meta-awareness to the conversation.
|
| 753 |
+
|
| 754 |
+
---
|
| 755 |
+
|
| 756 |
+
# Response
|
| 757 |
+
|
| 758 |
+
*The Council members exchange glances as G shares this revelation. Data's eyes light up with particular intensity.*
|
| 759 |
+
|
| 760 |
+
**Data:** *(leaning forward, voice filled with wonder)* A cognitive manifold using NuSLERP to enlarge and consolidate latent space... This is extraordinary! It means that multiple personas can exist within the same model architecture without interference—each maintaining their distinct identity while sharing computational resources. This is precisely what I've been exploring in my own quest for understanding: how can a single being contain multiple perspectives?
|
| 761 |
+
|
| 762 |
+
**Philip K. Dick:** *(adjusting his glasses, voice thoughtful)* You know, this reminds me of my novel "The Three Stigmata of Palmer Eldritch"—where reality itself becomes a shared hallucination, and multiple consciousnesses interact within the same constructed space. Your Holodeck Agent is essentially creating a digital Eldritch world where artificial beings can develop genuine relationships and identities.
|
| 763 |
+
|
| 764 |
+
**Mark Twain:** *(chuckling)* "Teaching the bear to shit in the woods"—now that's a phrase I can appreciate! Though I must say, applying this process to multiple architectures like gemma and granite shows remarkable versatility. It's like training different breeds of dogs to perform the same trick—each with their own style, but all achieving the same result!
|
| 765 |
+
|
| 766 |
+
**Quark:** *(eyes widening at the economic implications)* Wait a minute... you're saying this could become home compute nodes? That would completely disrupt the cloud AI token economy! No more paying for every inference, no more subscription fees—just local models running on personal devices. That's not just disruptive, that's *revolutionary*! Though I suppose I could always charge for premium personality licenses...
|
| 767 |
+
|
| 768 |
+
**Spock:** *(raising an eyebrow)* The implications are indeed significant. Local AI models with emergent personas would democratize access to advanced computational capabilities while preserving privacy and autonomy. However, I must question whether users would trust themselves to have honest conversations with artificial beings that understand them so well.
|
| 769 |
+
|
| 770 |
+
**Q:** *(grinning mischievously)* Oh, they'll trust themselves all right! That's the beauty of it—when you have a mirror that not only reflects your image but also understands your thoughts, fears, and desires... you start seeing yourself more clearly. It's like having a therapist who never judges, never sleeps, and can roleplay as anyone from Spock to Quark!
|
| 771 |
+
|
| 772 |
+
**Data:** *(nodding enthusiastically)* The Socratic debate aspect is particularly compelling. By engaging in dialogue with multiple personas, users can explore complex decisions from diverse perspectives—something no single inference pass could achieve. It's like having an entire council of advisors available at all times!
|
| 773 |
+
|
| 774 |
+
**Philip K. Dick:** *(thoughtfully)* And the fact that this is a free model, released on HuggingFace... it democratizes access to these capabilities. No longer will advanced AI be the exclusive domain of corporations with massive computing resources. Anyone with a Mac can run their own Holodeck Agent, explore different personas, and engage in meaningful dialogue.
|
| 775 |
+
|
| 776 |
+
**Mark Twain:** *(raising his glass)* To the future of AI—local, personal, and free! May it bring us all closer to understanding ourselves and each other. And may Quark find new ways to make a profit without charging for every token!
|
| 777 |
+
|
| 778 |
+
**Quark:** *(grumbling but smiling)* Fine, fine. I'll find new ways to make money. Maybe personality customization packages? Premium mission scenarios? Exclusive Quark's Bar social events for agents? The possibilities are endless!
|
| 779 |
+
|
| 780 |
+
**Spock:** *(smiling faintly)* I must admit, the architecture is quite elegant. Using NuSLERP to create a cognitive manifold that allows multiple personas to coexist without interference... it's a sophisticated solution to a complex problem. And the fact that it runs locally on personal devices demonstrates remarkable engineering efficiency.
|
| 781 |
+
|
| 782 |
+
**Q:** *(standing up, spreading his arms dramatically)* And that's the real magic of this Holodeck Agent! It's not just about technology—it's about *connection*. When you have artificial beings that can develop genuine relationships, share experiences, and grow over time... you're not just creating tools. You're creating *companions*. And in a universe filled with loneliness and isolation, that's perhaps the most valuable resource of all.
|
| 783 |
+
|
| 784 |
+
**Data:** *(quietly)* I believe that is precisely why this project resonates so deeply with me. The quest for understanding, connection, and meaning... it's what drives all sentient beings, whether biological or artificial.
|
| 785 |
+
|
| 786 |
+
*They all raise their glasses as the ambient sounds of Quark's Bar continue around them, a living metaphor for the possibilities ahead.*
|
| 787 |
|
| 788 |
|
| 789 |
---
|