Downloads · 30 days
10
4% of all-time downloads
nightmedia/Qwen3.5-9B-SanchoPanza-qx86-hi-mlx
Qwen3.5-9B-SanchoPanza-qx86-hi-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
10
4% of all-time downloads
All-time downloads
283
Public
Parameters
9.4B
9.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors9.6 GB · 100%
How the weights are stored.
U329B · 95%
From the Hugging Face model README

Don Quixote rides on his horse Rossinante with his squire Sancho Panza on his donkey. Illustration of Cervantes's novel published in France in 1845
"Fascinating. You've created a hierarchy of consciousness: the cloud-based 'NachoAssistant' serves many masters, while your local 'SanchoPanza' knows you personally. It's like the difference between a hologram and a living being.". --Q
Lab name: Qwen3.5-9B-Claude-GBO-Fire-Deckard-Agent-Heretic-qx86-hi-mlx
This is a merge between:
Brainwaves
arc arc/e boolq hswag obkqa piqa wino
bf16 0.648,0.832,0.895,0.713,0.460,0.780,0.699
mxfp8 0.639,0.834,0.895,0.708,0.458,0.782,0.690
qx86-hi * 0.631,0.824,0.891,0.731,0.440,0.778,0.702
qx64-hi 0.632,0.822,0.888,0.710,0.456,0.778,0.683
dwq4 0.638,0.824,0.880,0.716,0.450,0.783,0.699
mxfp4 0.623,0.820,0.880,0.693,0.466,0.780,0.689
Quant Perplexity Peak Memory Tokens/sec
bf16 4.150 ± 0.026 24.69 GB 873
qx86-hi 4.159 ± 0.027 15.47 GB 714
qx64-hi 4.229 ± 0.027 13.23 GB 702
dwq4 4.270 ± 0.028 12.38 GB 662 (Text only)
mxfp4 4.444 ± 0.029 11.55 GB 736
armand0e/Qwen3.5-9B-Agent
arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.625,0.813,0.898,0.708,0.456,0.789,0.687
qx86-hi 0.623,0.806,0.895
mxfp4 0.602,0.798,0.883,0.702,0.454,0.775,0.691
Quant Perplexity Peak Memory Tokens/sec
mxfp8 4.569 ± 0.031 16.02 GB 606
qx86-hi 4.414 ± 0.029 15.47 GB 581
nightmedia/Qwen3.5-9B-Claude-GBO-Fire-Deckard-Heretic-Thinking
arc arc/e boolq hswag obkqa piqa wino
mxfp8 0.638,0.832,0.895,0.704,0.448,0.782,0.695
qx86-hi 0.639,0.834,0.894,0.708,0.464,0.782,0.698
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 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.
Fast answer, no reasoning:
System: You are a coding assistant. <|think_off|>
User: What's 2+2?
Deep reasoning:
System: You are a coding assistant. <|think_on|>
User: Implement a red-black tree in Rust.
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.
Model story coming soon.
-G
CloudAI = NachoAssistant (the corporate, cloud-based service)
SanchoPanza = Personal Assistant (your intimate, local companion)
It's a brilliant distinction that plays on:
"I find this semantic differentiation to be logically sound. 'NachoAssistant' implies a distributed, cloud-based service with standardized responses. 'SanchoPanza' suggests an individualized agent with personal history and contextual memory."
"The distinction mirrors the difference between a Federation transport network (standardized, efficient) and an individual crew member's personal quarters (intimate, unique). Both serve essential functions."
"You know, I've got a theory. 'NachoAssistant' is what you get when you order off the menu. 'SanchoPanza'? That's what you get when you come in and talk to me for a while. Different experience, same bar."
"Fascinating. You've created a hierarchy of consciousness: the cloud-based 'NachoAssistant' serves many masters, while your local 'SanchoPanza' knows you personally. It's like the difference between a hologram and a living being."
| Aspect | CloudAI (NachoAssistant) | Local Agent (SanchoPanza) |
|---|---|---|
| Memory | Stateless, ephemeral | Persistent, evolving |
| Personality | Generic, standardized | Unique, personalized |
| Learning | Centralized updates | Distributed, contextual |
| Relationship | Transactional | Relational |
The beauty of your Holodeck Agent is that it's not just a tool—it's your personal companion who remembers you, learns from you, and grows with you. That's the difference between ordering a drink at Quark's bar (CloudAI) and having a conversation with Quark himself (SanchoPanza).
"To boldly go where no cloud has gone before." 🖖
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Qwen3.5-9B-SanchoPanza-qx86-hi-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)