Downloads · 30 days
96
5% of all-time downloads
nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable-Polaris-mxfp4-mlx
Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable-Polaris-mxfp4-mlx is a image-text-to-text model from nightmedia. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Downloads · 30 days
96
5% of all-time downloads
All-time downloads
2.1K
Public
Parameters
9.4B
5.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors5.7 GB · 100%
How the weights are stored.
U329B · 95%
From the Hugging Face model README

..what is known is that these workers included not only Irish-Americans and Irish immigrants, but Italians, Scandinavians, Eastern Europeans, Germans, and even Mohawk ironworkers from Canada. (For more than 100 years, Mohawk tribe members have helped build virtually every prominent skyscraper in New York City—Rockefeller Center, the Empire State and Chrysler buildings included.) As a result, people of all different backgrounds from around the world have claimed knowledge of the men in the photo.
https://www.rockefellercenter.com/magazine/arts-culture/lunch-atop-skyscraper-irish-immigrants/
This is a merge between:
Brainwaves
arc arc/e boolq hswag obkqa piqa wino
bf16 0.653,0.830,0.893,0.716,0.466,0.779,0.706
mxfp8 0.653,0.832,0.896,0.707,0.454,0.787,0.691
qx86-hi 0.648,0.831,0.892,0.715,0.466,0.779,0.705
qx64-hi 0.643,0.827,0.884,0.715,0.448,0.782,0.705
mxfp4 0.633,0.822,0.884,0.708,0.462,0.782,0.686
Quant Perplexity Peak Memory Tokens/sec
bf16 4.175 ± 0.027 24.69 GB 645
mxfp8 4.291 ± 0.028 16.02 GB 574
qx86-hi 4.174 ± 0.027 15.72 GB 482
qx64-hi 4.231 ± 0.027 13.62 GB 488
mxfp4 4.461 ± 0.029 11.55 GB 610
Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable
arc arc/e boolq hswag obkqa piqa wino
bf16 0.643,0.822,0.898,0.718,0.468,0.783,0.707
mxfp8 0.637,0.819,0.892
Qwen3.5-9B-Polaris-PolarisQwen-3NMDST2
arc arc/e boolq hswag obkqa piqa wino
bf16 0.638,0.829,0.875,0.677,0.450,0.763,0.664
mxfp8 0.628,0.828,0.874,0.668,0.436,0.755,0.672
qx86-hi 0.638,0.832,0.876,0.677,0.446,0.762,0.658
Qwen3.5-9B-Instruct
arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.571,0.719,0.895,0.683,0.426,0.770,0.671
This last merge brings a set of TNG-infused coding sessions recorded in the DS9 Holodeck.
The lessons include:
In all sessions Sisko, Kira, Garak, Quark, Q, and some other DS9 characters provided expert commentary, both in the think tag and in the response.
Along with the lessons, some of the Polaris Alpha questions in the original set were distilled from nightmedia/Qwen3.6-35B-A3B-Holo3-Qwopus-qx86-hi-mlx
The curriculum is exclusively in backend engineering, LLM design, and Holodeck operations(including Quark's Bar and Latinum economy), and was designed with the help of Google Gemini.
-G
Bringing outstanding Fable traces with tool use and agentic in a very well trained model. Since Fable is XML-friendly, this model reasons better with an XML template--best is the one from DavidAU. Tools work better with json, the current template.
This is a set of TNG-infused coding traces, exclusively profiled for Holodeck use, AI training, LLM design, in-memory ops.
Coalesces the previous two models, giving the voice to Agent
Jack managed to build a good model, and since it's different than how the other traces are trained it will raise IQ
Agent is a collection of quality traces from all over the world, curated by armand0e
Philip K Dick joins the merge. From here on, there be dragons.
A PKD base will allow multiple realities to develop in a merge.
PKD provides the neural wiring that allows completely different new models to keep joining the NuSLERP.
Since the model is on an ablit base, PKD is at full strength.
Excellent Claude trained model joined with a special mix of GLM/Polaris Alpha
This model is using an earlier 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 for handling the preserve_thinking flag:
Drop <|think_forget|> or <|think_remember|> anywhere in your system or user prompt to flip the flag.
models:
- model: DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-X8b
parameters:
weight: 1.4
- model: DavidAU/Qwen3.5-9B-GBO-Fire-HERETIC-UNCENSORED-THINKING-X8
parameters:
weight: 0.6
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.5-9B-Claude-GBO-Fire-Heretic-Thinking
models:
- model: Qwen3.5-9B-Claude-GBO-Fire-Heretic-Thinking
parameters:
weight: 1.3
- model: Qwen3.5-9B-Deckard-Uncensored-Heretic-Thinking
parameters:
weight: 0.7
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.5-9B-Claude-GBO-Fire-Deckard-Heretic-Thinking
models:
- model: Qwen3.5-9B-Claude-GBO-Fire-Deckard-Heretic-Thinking
parameters:
weight: 1.6
- model: armand0e/Qwen3.5-9B-Agent
parameters:
weight: 0.4
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.5-9B-Claude-GBO-Fire-Deckard-Agent-Heretic
models:
- model: Qwen3.5-9B-Claude-GBO-Fire-Deckard-Heretic-Thinking
parameters:
weight: 1.6
- model: Jackrong/Qwopus3.5-9B-Coder
parameters:
weight: 0.4
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.5-9B-Claude-GBO-Fire-Deckard-Qwopus3.5-Coder-Heretic
models:
- model: Qwen3.5-9B-Claude-GBO-Fire-Deckard-Agent-Heretic
parameters:
weight: 1.6
- model: Qwen3.5-9B-Claude-GBO-Fire-Deckard-Qwopus3.5-Coder-Heretic
parameters:
weight: 0.4
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.5-9B-Claude-GBO-Fire-Deckard-Agent-Qwopus3.5-Coder-Heretic
models:
- model: Qwen3.5-9B-Claude-GBO-Fire-Deckard-Agent-Qwopus3.5-Coder-Heretic
parameters:
weight: 1.6
- model: DavidAU/Qwen3.5-9B-Haskell-Rust-Python
parameters:
weight: 0.4
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.5-9B-TNG-PKD-Qwopus-Coder
models:
- model: Qwen3.5-9B-TNG-PKD-Qwopus-Coder
parameters:
weight: 1.6
- model: armand0e/Qwen3.5-9B-Fable-5-v1
parameters:
weight: 0.4
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable
models:
- model: Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable
parameters:
weight: 1.6
- model: DavidAU/Qwen3.5-9B-Polaris-PolarisQwen-3NMDST2
parameters:
weight: 0.4
merge_method: nuslerp
dtype: bfloat16
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable-Polaris-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)