Nano_Imp_1B

It's the 10th of May, 2025—lots of progress is being made in the world of AI (DeepSeek, Qwen, etc...)—but still, there has yet to be a fully coherent 1B RP model. Why?

Well, at 1B size, the mere fact a model is even coherent is some kind of a marvel—and getting it to roleplay feels like you're asking too much from 1B parameters. Making very small yet smart models is quite hard, making one that does RP is exceedingly hard. I should know.

I've made the world's first 3B roleplay model—Impish_LLAMA_3B—and I thought that this was the absolute minimum size for coherency and RP capabilities. I was wrong.

One of my stated goals was to make AI accessible and available for everyone—but not everyone could run 13B or even 8B models. Some people only have mid-tier phones, should they be left behind?

A growing sentiment often says something along the lines of:

If your waifu runs on someone else's hardware—then she's not your waifu.

I'm not an expert in waifu culture, but I do agree that people should be able to run models locally, without their data (knowingly or unknowingly) being used for X or Y.

I thought my goal of making a roleplay model that everyone could run would only be realized sometime in the future—when mid-tier phones got the equivalent of a high-end Snapdragon chipset. Again I was wrong, as this changes today.

Today, the 10th of May 2025, I proudly present to you—Nano_Imp_1B, the world's first and only fully coherent 1B-parameter roleplay model.

Example dialogue (3-shot):

Included Character cards in this repo:

Nano_Imp (A shrunken palm-sized hellspawn who wants your soul)

Other character cards:

Takai_Puraisu (Car dealership simulator)
Vesper (Schizo Space Adventure)
Shmena Koeset (An overweight and foul-mouthed troll huntress with a bad temper.)
Nina_Nakamura (The sweetest dorky co-worker)
Employe#11 (Schizo workplace with a schizo worker)

TL;DR

The first and only 1B RP model in the world.
Runs on anything. Don't have a GPU, you can run Nano_Imp_1B on an old CPU from 10 years ago no problem.
Short length response (1-2 paragraphs, usually 1), CAI style.
Surprisngly coherent, the need of swipes is inveitable though.
quite good at following the character card, this assumes sane generation settings, and once it picked up the formatting- this is important. Try the included characters if you're having sub-optimal results.

Important: Make sure to use the correct settings!

Assistant settings

Roleplay settings

Nano_Imp_1B is available at the following quantizations:

Original: FP16
GGUF: GGUF
GPTQ: 4-Bit-32
Specialized: FP8
Mobile (ARM): Q4_0

Model Details

Intended use: Role-Play, Basic Creative Writing, Basic General Tasks.
Censorship level: Medium
4.5 / 10 (10 completely uncensored)

UGI score:

Pending

Recommended settings for assistant mode

Full generation settings: Debug Deterministic.

Full generation settings: min_p.

Recommended settings for Roleplay mode

Settings for RP, click below to expand:

Roleplay settings:

A good repetition_penalty range is between 1.12 - 1.15, feel free to experiment.

With these settings, each output message should be neatly displayed in 1 - 5 paragraphs, 2 - 3 is the most common. A single paragraph will be output as a response to a simple message ("What was your name again?").

min_P for RP works too but is more likely to put everything under one large paragraph, instead of a neatly formatted short one. Feel free to switch in between.

(Open the image in a new window to better see the full details) Oni_Mitsubishi_12B_Settings

temperature:  0.8
top_p:  0.95
top_k:  25
typical_p:  1
min_p:  0
repetition_penalty: 1.12
repetition_penalty_range: 1024

Roleplay format: Classic Internet RP

*action* speech *narration*

min_p will bias towards a single big paragraph.
The recommended RP settings will bias towards 1-3 small paragraphs (on some occasions 4-5)

Model instruction template: Llama-3-Instruct

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>

Other recommended generation Presets:

Midnight Enigma

max_new_tokens: 512
temperature: 0.98
top_p: 0.37
top_k: 100
typical_p: 1
min_p: 0
repetition_penalty: 1.18
do_sample: True

Divine Intellect

max_new_tokens: 512
temperature: 1.31
top_p: 0.14
top_k: 49
typical_p: 1
min_p: 0
repetition_penalty: 1.17
do_sample: True

simple-1

max_new_tokens: 512
temperature: 0.7
top_p: 0.9
top_k: 20
typical_p: 1
min_p: 0
repetition_penalty: 1.15
do_sample: True

Your support = more models

My Ko-fi page (Click here)

Citation Information

@llm{Nano_Imp_1B,
  author = {SicariusSicariiStuff},
  title = {Nano_Imp_1B},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/SicariusSicariiStuff/Nano_Imp_1B}
}

Other stuff

SLOP_Detector Nuke GPTisms, with SLOP detector.
LLAMA-3_8B_Unaligned The grand project that started it all.
Blog and updates (Archived) Some updates, some rambles, sort of a mix between a diary and a blog.

SicariusSicariiStuff
/

Nano_Imp_1B