Qwen3.6-35B-A3B-Fable-Holo3.1-mxfp4-mlx

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

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.

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

Photo: "Dante's Inferno--The Market Of Souls", Nikon/Noct/Photoshop by G

---

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Qwen3.6-35B-A3B-Fable-Holo3.1-mxfp4-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)