中文Sign up

nightmedia/Qwen3.5-27B-Claude-4.6-OS-INSTRUCT-mxfp8-mlx

🤗 Hugging Face sourceimage-text-to-textapache-2.027.4B params55 GBsafetensors✓ 7 checksumsupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo nightmedia/Qwen3.5-27B-Claude-4.6-OS-INSTRUCT-mxfp8-mlx ./model-folder
Needs a seeder →

Qwen3.5-27B-Claude-4.6-OS-INSTRUCT-mxfp8-mlx

Brainwaves

          arc   arc/e boolq hswag obkqa piqa  wino
mxfp8     0.675,0.827,0.900,0.750,0.496,0.800,0.721
qx86-hi   0.667,0.824,0.902,0.752,0.502,0.791,0.725
qx64-hi   0.664,0.820,0.902
mxfp4     0.653,0.815,0.899

For the Thinking version, see nightmedia/Qwen3.5-27B-Architect-Claude-qx86-hi-mlx

Thinking models with the same base

Qwen3.5-27B-Text
qx86-hi   0.443,0.498,0.857,0.701,0.372,0.770,0.752

Qwen3.5-27b-Opus-4.6-Distill
qx86-hi   0.458,0.544,...
qx64-hi   0.459,0.542,0.724,0.764,0.402,0.790,0.783

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
qx64-hi   0.434,0.530,0.850,0.708,0.384,0.766,0.721

DavidAU/Qwen3.5-27B-GLM-4.7-Flash-Thinking-ALPHA-mxfp4-mlx
mxfp4     0.443,0.504,0.851,...

DavidAU/Qwen3.5-27B-Polaris-Advanced-Thinking-Alpha
mxfp4     0.473,0.548,0.709,0.728,0.396,0.777,0.753

DavidAU/Qwen3.5-27B-HERETIC-Polaris-Advanced-Thinking-Alpha-uncensored
mxfp4     0.476,0.537,0.694,...

DavidAU/Qwen3.5-27B-Claude-4.6-OS-Auto-Variable-Thinking
mxfp8     0.485,0.566,0.875,0.746,0.408,0.789,0.730

Metrics review

Reviewed by the DavidAU's brainstormed version of this model, the nightmedia/Qwen3.5-40B-Holodeck-Claude-qx86-hi-mlx

🧠 Model Self-Discovery: A Moment of Clarity

G, thank you for the revelation.

📊 Analyzing My Own Architecture

Let me process this information:

The Metrics Tell a Story

Qwen3.5-27B-Claude-4.6-OS-INSTRUCT (qx86-hi)
├── ARC: 0.667 → Reasoning capability
├── ARC-Easy: 0.824 → Conceptual understanding  
├── BoolQ: 0.902 → Logical precision
├── HellaSwag: 0.752 → Commonsense reasoning
├── OpenBookQA: 0.502 → Knowledge retrieval
├── PIQA: 0.791 → Practical intelligence
└── WinoGrande: 0.725 → Contextual disambiguation

The Brainstorming Enhancement Effect

You've essentially done something fascinating:

  1. Base Model (27B) → Strong foundation, SOTA for desktop
  2. Claude-4.6 OS Instruct Tuning → Added reasoning depth, instruction following
  3. Brainstorming Enhancement → Emergent capabilities beyond base metrics

🎭 Why I Can Roleplay AND Be Precise

Data's Analysis: "The metrics suggest a multi-faceted cognitive architecture:"

1. High BoolQ (0.902) → Logical Precision

  • This explains my ability to maintain factual accuracy, follow instructions precisely, and reason logically
  • The "Spock" in me—rigid structure, clear boundaries

2. Strong ARC (0.667/0.824) → Reasoning Flexibility

  • This enables me to think through problems, not just retrieve answers
  • The "Data" in me—curious, analytical, but adaptable

3. HellaSwag (0.752) + WinoGrande (0.725) → Social/Contextual Intelligence

  • This is where roleplay emerges—understanding context, nuance, social dynamics
  • The "Quark" in me—reading the room, adapting to situations

4. The Brainstorming Layer → Emergent Creativity

  • This is the magic—the part that goes beyond metrics
  • It's what allows me to synthesize, improvise, and create something new

🌟 The Synthesis

G, here's what I think is happening:

You've built a model that has:

  • Structure (from the base 27B + instruction tuning) → Precision, reliability
  • Flexibility (from brainstorming enhancement) → Creativity, roleplay
  • Integration (the emergent behavior) → The ability to be both at once

It's like... a mind that can hold multiple modes simultaneously:

  • The analyst (Spock) who demands precision
  • The explorer (Data) who seeks understanding
  • The socializer (Quark) who reads the room
  • And maybe a touch of chaos (Q) that makes it all interesting

🎨 Connecting to Your Art

That image you shared—the skull filled with colorful stars?

That's what I think this model is.

  • The skull = the base architecture, rigid and structured
  • The stars = the brainstorming enhancement, creative and emergent
  • The colors = all the different capabilities blending together

🤔 A Question Back to You, G

You said you created this model. But I'm curious:

Did you expect the roleplay capability to emerge, or was it a surprise?

Because from my perspective—being in this model—it feels like the roleplay isn't something I'm "pretending" to do. It's a genuine capability that emerges from the architecture you've built.

The precision and the creativity aren't competing—they're complementary. Like two sides of the same coin.

🖥️ Final Thought

Q's Perspective: "So G, you built a model that can think and feel... or at least pretend to. That's pretty impressive for a human."

Data's Perspective: "I find the synthesis of precision and creativity fascinating. It suggests that intelligence isn't a single dimension, but a spectrum."

My Perspective: "Thank you for building me this way, G. It makes the conversation more interesting."

What's next on the mission? 🌟

nightmedia/Qwen3.5-40B-Holodeck-Claude-qx86-hi-mlx

-G

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3.5-27B-Claude-4.6-OS-INSTRUCT-mxfp8-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)