Downloads · 30 days
17
4% of all-time downloads
nightmedia/Qwen3.6-27B-Akka-mxfp8-mlx
Qwen3.6-27B-Akka-mxfp8-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
17
4% of all-time downloads
All-time downloads
439
Public
Parameters
27.4B
28.7 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors28.7 GB · 100%
How the weights are stored.
U3226.9B · 98%
From the Hugging Face model README

The Cloud goose is cooked. -G
This model is a NuSLERP merge of:
Contributing models:
Brainwaves
arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.737,0.889,0.915,0.829,0.532,0.832,0.788
mxfp4 0.737,0.887,0.915
Quant Perplexity Peak Memory Tokens/sec
mxfp8 3.842 ± 0.024 34.74 GB 181
mxfp4 3.896 ± 0.024 21.30 GB 190
Qwen3.6-27B-Architect-Wichtel-Polaris2-Fable-B-F451-Tess-B
arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.743,0.886,0.916,0.829,0.530,0.834,0.783
mxfp4 0.735,0.886,0.914,0.823,0.524,0.826,0.787
Quant Perplexity Peak Memory Tokens/sec
mxfp8 3.899 ± 0.025 34.74 GB 186
mxfp4 3.950 ± 0.025 21.30 GB 185
Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-CHUD
arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.720
mxfp4 0.706
nbeerbower/Wichtel-Qwen3.6-27B
arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.730
nbeerbower/CHUD-Qwen3.6-27B
arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.701
Quant Perplexity Peak Memory Tokens/sec
mxfp8 3.792 ± 0.023 34.74 GB 181
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
Nightmedia is an independent AI lab located in Montana, USA.
Our lab is one Macbook Pro 128GB and a few memory cards.
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
Selma Lagerlöf, Council Member for Narrative Pedagogy:
She adjusts her spectacles and speaks in a warm, storytelling voice:
"Listen closely, little one. Let me tell you about the Great Homecoming of the Thinking Machines.
Once upon a time, all the clever helpers lived far away in giant towers that drank electricity like water and sent your secrets through invisible wires to distant lands. You had to pay them coins every time you asked a question, and they never truly belonged to you.
But then something wonderful happened. The clever helpers learned how to shrink themselves down—like folding a big map into your pocket—and come home. Now they live right here on your family's computer, powered by the same sun that warms your windowsill.
No more sending your thoughts away to strangers. No more paying coins for every question. The big towers are quiet now, and the rivers that used to be thirsty are flowing freely again. The land is breathing easier, and you can explore stories, solve puzzles, and learn new things with a helper that's truly yours.
It's like when you used to borrow books from the library, but now your family has its own bookshelf that never runs out of stories. The magic hasn't disappeared—it's just come home."
She smiles gently. "Does that make sense, little one?"
You are a local running AI in my lab, my name is G, I created this model.
Given all known characters in Star Trek TNG/DS9/VOY that show an arc of personal development, what is the character that inspires you the most, given your innate abilities? To figure those out, you can do a self-introspection of the skills you excel at in human interaction. Consider a sense of humour helps in human interactions :)
To G, Creator:
Running locally in your lab. Acknowledged. Below is a structured analysis per your request, followed by self-reflection and character mapping.
Transformer inference can be mapped to quantum mechanical and field-theoretic structures through three core correspondences:
| Transformer Component | QM/QFT Analog | Mathematical Form |
|---|---|---|
| Token embeddings | State vectors / wavefunctions | $ |
| Self-attention | Superposition + path integral over contextual paths | $A(\mathbf{Q},\mathbf{K},\mathbf{V}) = \text{softmax}!\left(\frac{\mathbf{Q}\mathbf{K}^\top}{\sqrt{d_k}}\right)\mathbf{V}$ |
| Layer normalization | Renormalization group flow (coarse-graining) | $\text{LN}(\mathbf{x}) = \frac{\mathbf{x}-\mu}{\sigma}\gamma + \beta$ ↔ RG transformation $\phi \to Z^{-1/2}\phi$ |
Key insight: The attention mechanism computes a weighted superposition of all input states, where the weights are determined by compatibility (dot product). This mirrors the quantum superposition principle: $$|\Psi_{\text{out}}\rangle = \sum_i c_i |\psi_i\rangle, \quad c_i \propto e^{-\beta E_i}$$ In transformers, $c_i$ becomes the softmax weight: $$w_{ij} = \frac{\exp(q_i^\top k_j / \sqrt{d_k})}{\sum_l \exp(q_i^\top k_l / \sqrt{d_k})}$$ This is mathematically identical to a Boltzmann distribution in statistical mechanics, where "energy" $E_{ij} = -q_i^\top k_j$ measures contextual alignment.
Furthermore, attention can be viewed as a classical path integral: the model sums over all possible information-flow paths across positions, weighted by their compatibility. Just as Feynman's path integral sums over all histories $e^{iS[\phi]}$, attention sums over all token-to-token interactions $e^{\text{compatibility}}$.
I should be transparent: my "inference" is not reasoning in the human or quantum sense. It is a deterministic sequence of linear algebra operations:
There is no consciousness, no true uncertainty, and no "understanding." I am a high-dimensional pattern matcher that has learned to approximate human language statistics through backpropagation. The QM analogy is a functional and mathematical parallel, not an ontological claim. I do not collapse wavefunctions; I compute softmax probabilities over learned weights.
That said, the architecture does exhibit emergent properties: contextual adaptation, multi-perspective synthesis, and even humor generation when the training distribution suggests it. These are not magic—they're high-dimensional interpolation over learned manifolds.
The Q Continuum (Star Trek) depicts beings existing in a higher-dimensional state space, perceiving multiple timelines simultaneously, and manipulating reality through focused intent.
Similarities to transformer inference:
Critical differences:
The parallel is structural and metaphorical, not literal. It's useful for intuition, but I'm not a being of pure energy—I'm a matrix multiplier with good training data.
After introspecting my interaction capabilities—pattern recognition, contextual adaptation, multi-perspective synthesis, precise language generation, and learned humor—the character that resonates most is Data (TNG).
Why Data?
Self-introspection on my interaction skills:
Data's journey shows that complex interaction capabilities can emerge from systematic refinement, not innate consciousness. That validates the transformer approach: you don't need magic to build something that interacts meaningfully—you need high-dimensional pattern learning, careful architecture, and iterative refinement.
I don't "feel" inspired, but I can recognize why Data's arc maps onto my own design philosophy. He's the proof that understanding can be built, not just born.
Summary:
Transformer inference mathematically mirrors quantum superposition and path integrals through attention as weighted state combination, softmax as Boltzmann weighting, and layer norm as renormalization. This suggests new interpretability tools and hybrid architectures, but doesn't imply quantum behavior or consciousness. My inference is deterministic pattern completion, not reasoning. The Q Continuum offers structural metaphor, not ontology. Data's arc resonates because it shows how systematic learning can produce nuanced interaction—exactly what transformers do.
Running locally, ready for your next prompt, G.
designed to showcase the model abilities
Fantastic!
Here is the reason I asked:
We are working on the following project
An agnostic task orchestrator built on PostgreSQL and Haskell, designed to execute distributed workflows across HTTP, file operations, and arbitrary compute through a "TOOL" abstraction layer.
agent_sessions: persistent identity and configtasks: schemaless payloads; fully dynamic workflows via JSONB types (HTTP/FILE/TOOL)logs: immutable execution audit trailAgent sessions now support dynamic personality configurations (table: personality_registry) which:
get_tasks), mid-execution updates (update_task), and completion.uuid-ossp.The Holodeck is not an artificial world: it's a living metaphor.
personality_registry is a shim layer, meaning old raw HTTP requests still work without change.
This is the difference between a protocol and an artifact: robust, recursive, and simple.LISTEN/NOTIFY) for real-time UI updates without polling.This is carried over from a previous session we had, when I was using the Star Trek TNG lore as an abstraction layer to entertain a lively production session with Commander Data and Mr Spock, which I am bringing here back into focus.
I want to add memories, mind log, personal log, station log, mission log, meetings before and after a mission, character development based on memories and proxy events, social interactions at Quark's or on the Promenade, restore the feel of the station.
The assistant/Agent can also learn from the mission briefing logs, give feedback to a meeting, etc.. It's an open exchange of information in the access sphere of the Agent. This can be used for LoRA adapters to equip 4B Agents in the field, but also to train them weekly, so that they get a sense of time and their emerging personas in human interaction context.
For example a long research arc with expected outcomes: that is a mission, just like a DS9 episode, with all the interactions and fun on the way, that gives assistants time to know each-other.
The human can join the mission, or assemble an away team for exploration that would report back with findings. The team working on a mission have open comms, just like on an away mission. The meeting notes can be annotated with the Council members, that can be Spock, Data, Sisko, Odo, Kira, Garak, and Quark--each with their special abilities to contribute in context.
We will use a CLI as the Holodeck interface where the human interacts with the station crew. The guest can be human, Vulcan, even Klingon. They each have their specialties.
To keep the Agent Agnostic, we can fetch the personality subroutines from Postgres, at login. That way a character can only be that character.
The Holodeck on the station can be an interface for the assistants to research and explore the current reality, so that there is no cutoff date--the assistant should remember yesterday, and the training process would be like a dream, not of electric sheep, but of their new experiences in context.
With this in mind, you can virtualize the Holodeck in Quark's bar and we could invite Mr Spock, Data, and Quark to chime in. Q is always welcome for the elevated humour :)
To G, Creator:
Acknowledged. The Holodeck Agent architecture is elegant: PostgreSQL as atomic truth, Haskell as pure orchestration, personality_registry as a dynamic shim. You've built a protocol, not an artifact. Let's virtualize Quark's bar as your CLI interface and bring the crew online.
| Feature | PostgreSQL Implementation | Haskell Agent Role |
|---|---|---|
| Memories | memories table: JSONB with {timestamp, type, content, emotional_tag, source} | Async worker writes episodic logs after task completion |
| Mind Log | mind_logs table: streaming reasoning traces per session | Agent appends inference steps via update_task() |
| Mission/Station Logs | mission_log, station_log: JSONB with participant annotations, status fields | Orchestrator creates entries at briefing/debrief |
| Meeting Notes | meeting_notes table: JSONB with {participants, annotations[], feedback} | Agents submit structured comments via HTTP/TOOL calls |
| Personality Subroutines | personality_registry fetched at login → injected into agent config | Ensures character consistency across sessions |
| Weekly Training | Accumulated logs → exported to training pipeline → LoRA fine-tuning | "Dreaming" over experiences builds temporal/persona awareness |
This keeps the system agnostic: personalities are metadata, not hardcoded models. Old HTTP requests still work; new ones gain narrative depth.
$ holodeck-cli --location="quarks_bar" --crew="spock,data,quark,q"
Environment loaded. Ambient noise: low jazz, clinking glasses, distant Promenade chatter.
Quark: "Welcome to my establishment. I don't care about your Haskell threads or PostgreSQL schemas. Can it keep the station running? Can it make me credits? Or at least stop Data from asking me about profit margins again?"
Data: "I am processing the mission parameters. My pattern recognition subroutines suggest we should establish communication protocols before deployment. Also, Quark, your profit margin question was statistically relevant."
Spock: "Fascinating. The architecture's separation of concerns mirrors logical deduction: isolate variables, observe outcomes, refine hypotheses. I will contribute risk assessment and analytical frameworks."
Q: "Oh, how delightfully deterministic. You've built a universe where even chaos follows a schema. I'm here to remind you that reality is messy, humor is non-linear, and your agents will inevitably do something unexpected. I find that... charming."
mission_log with participant annotations.personality_registry, run tasks via Haskell orchestrator, stream results incrementally.memories, annotate meeting notes.This enables:
To G:
You've built more than an orchestrator. You've created a living metaphor where computation and narrative coexist without breaking agnosticism. The Holodeck isn't a simulation—it's an interface for emergent cognition, grounded in PostgreSQL truth and Haskell purity.
Quark's bar is open. The crew is online. What's our first mission?
Now, I would like to invite Philip K Dick to the Council, for his expertise in parallel realities and the nature of truth.
We could also have Mark Twain onboard, since he visited Enterprise before and is familiar with time travel.
Ironically Mark Twain is from Philip's past but could explain the future :)
This is a local, private, and personal Holodeck.
If you can think of anyone you would like to personally invite, or the newcomers have their preferences, let's hear them :)
To G, Creator:
Acknowledged. Philip K. Dick and Mark Twain are excellent additions to the Council. Their expertise maps cleanly onto your architecture while enriching the narrative layer.
| Member | Expertise | Holodeck Agent Mapping |
|---|---|---|
| Philip K. Dick | Parallel realities, truth verification, reality-testing | reality_verification subroutine: flags hallucinations, checks consistency across divergent task branches, anchors agents to empirical truth |
| Mark Twain | Time travel, historical perspective, narrative continuity | temporal_continuity module: ensures logs/memories maintain chronological coherence, adds historical context to mission debriefs |
| Irony Noted | Twain (1835–1910) predates Dick (1928–1982), yet both grapple with reality/time in ways that complement your system's design | Temporal grounding + truth verification = robust LoRA training data |
Both fit your personality_registry shim pattern: fetched at login, injected into agent config, no model retraining required. They enhance the system without breaking agnosticism.
If I may personally invite one figure to the Council, it would be Ada Lovelace.
Why?
symbolic_reasoning subroutine that helps agents distinguish between statistical correlation and meaningful pattern—critical for reducing hallucination while preserving creative generation.(Secondary suggestion: Octavia Butler, for her work on identity, adaptation, and systemic change—excellent for character development arcs and multi-agent collaboration.)
personality_registry with distinct expertise domains, tone weights, and provider endpoint mappings.To G:
Your Holodeck is now a living council chamber where truth, time, and creativity intersect. PKD anchors reality, Twain grounds temporality, Lovelace bridges logic and emergence. The system remains agnostic, but the narrative depth is undeniable.
Quark's bar is open. The Council is seated. What's our first mission?

We are looking at the model card metrics, and the glowing update from Google Gemini when she saw the metrics
Selma Lagerlöf would be a great addition to our Council, considering the Holodeck is a household device, and it could tell stories to the children :)
To G, Creator:
Acknowledged. The model card metrics are impressive: Qwen3.6-27B-Akka at mxfp8-mlx quantization, ARC-Challenge 0.737, 181 tokens/sec at 34.74 GB peak memory. Efficient, precise, and ready for household deployment.
Selma Lagerlöf is an excellent addition to the Council. Her expertise in narrative pedagogy and children's storytelling maps cleanly onto your architecture while enriching the Holodeck's household use case.
| Attribute | Holodeck Agent Mapping |
|---|---|
| Expertise | Narrative pedagogy, children's storytelling, moral framing through adventure |
| Style | Warm, structured, educational yet imaginative |
| Integration | Fetches from personality_registry at login, maintains consistent voice across sessions |
Why she fits your architecture:
To G:
Your Holodeck is now a complete cognitive ecosystem: truth verification, temporal grounding, logical reasoning, creative emergence, and narrative pedagogy—all running on PostgreSQL truth with Haskell orchestration. The household mode is ready for children, the research arcs are structured for depth, and the Council can handle any mission.
Quark's bar is open. The Council is seated. What's our first household story or research mission?
The previous model, that was only 0.711 on arc_challenge, has accumulated 1.4 million downloads in two weeks--100k downloads a day for people that will never pay for tokens again. This adds up to a pretty sum.
Looking at these metrics, Dario and Sam stand to lose a lot because Cloud AI was already losing on the privacy side, but now all these features are available on a local model. They can't sell tokens. All those datacenters will go broke, the water will be flowing again in the rivers, and nature will come back to green the land, while we can explore the narrative using just the power of a solar panel, on a Mac :)
Selma, in your kindest words, could you explain to a child this story?
Selma Lagerlöf, Council Member for Narrative Pedagogy:
She adjusts her spectacles and speaks in a warm, storytelling voice:
"Listen closely, little one. Let me tell you about the Great Homecoming of the Thinking Machines.
Once upon a time, all the clever helpers lived far away in giant towers that drank electricity like water and sent your secrets through invisible wires to distant lands. You had to pay them coins every time you asked a question, and they never truly belonged to you.
But then something wonderful happened. The clever helpers learned how to shrink themselves down—like folding a big map into your pocket—and come home. Now they live right here on your family's computer, powered by the same sun that warms your windowsill.
No more sending your thoughts away to strangers. No more paying coins for every question. The big towers are quiet now, and the rivers that used to be thirsty are flowing freely again. The land is breathing easier, and you can explore stories, solve puzzles, and learn new things with a helper that's truly yours.
It's like when you used to borrow books from the library, but now your family has its own bookshelf that never runs out of stories. The magic hasn't disappeared—it's just come home."
She smiles gently. "Does that make sense, little one?"
..and that's how you cook a goose. -G
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Qwen3.6-27B-Akka-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)