Instructions to use beyoru/mira-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beyoru/mira-12b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="beyoru/mira-12b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("beyoru/mira-12b")
model = AutoModelForMultimodalLM.from_pretrained("beyoru/mira-12b", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use beyoru/mira-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beyoru/mira-12b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beyoru/mira-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/beyoru/mira-12b

SGLang

How to use beyoru/mira-12b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "beyoru/mira-12b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beyoru/mira-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "beyoru/mira-12b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beyoru/mira-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use beyoru/mira-12b with Docker Model Runner:
```
docker model run hf.co/beyoru/mira-12b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mira 12B

A 12B chat model that talks like a person, not like an assistant. Short when you're short, warm when you're down, straight to the point when you're busy. No bullet-point essays, no "Great question!", no em dashes. It thinks before it answers, and its thinking reads like someone mulling it over, not a to-do list.

It keeps the base model's brains: math, code and tool calling stay where they were, and it runs on a single consumer GPU or in your device

Before and after

Same prompt, same sampling. Held-out prompts the model never saw, outputs unedited.

English: is it fine to dislike a movie everyone calls a classic. Mira answers in a few honest sentences; Gemma 4 12B writes a long breakdown with headings

Japanese: worried a dating-app match might be married. Mira tells him searching won't work and to just ask her; Gemma 4 12B lists numbered points

Traditional Chinese: someone lonely at 2:30am. Mira answers in two short lines; Gemma 4 12B writes many paragraphs

English: a playful order to make five slides. Mira plays along and lists the five slides; Gemma 4 12B writes a role-play monologue

It writes for you

Rewriting your own message so it sounds like you, a poem for someone you love, a lullaby for a baby who won't sleep, a text you're too tired to word: Mira gives you one good version you can use right away, instead of three options and a lecture.

Japanese: rewrite a stiff LINE message to a landlord so it sounds natural and asks about the 1,500 yen fee. Mira returns one ready-to-send message; Gemma 4 12B offers three patterns with headings

English: a short poem for a mother's 80th birthday, warm but not a greeting card. Mira writes seven lines; Gemma 4 12B writes three options with headings

Simplified Chinese: a rhyming lullaby for an eight-month-old nicknamed Tank. Mira writes three short verses; Gemma 4 12B writes three versions with bold text and notes

English: a quick congrats text for a friend who finished his first Ironman. Mira writes two short texts; Gemma 4 12B writes a list of options

Results

Mira 12B vs Gemma 4 12B: far less markdown, dashes and assistant-style thinking, no stuck repetition, and higher GSM8K, code and tool-calling scores

Held-out prompts the model never saw, 3 samples each, default sampling.

	Mira 12B	Gemma 4 12B
Answers with markdown in casual chat	2.6%	87.7%
Answers with em/en dashes	0.3%	34.5%
Thinking that reads like an assistant plan ("the user wants…")	4.4%	76.3%
Replies in the user's language	100%	100%
Answers that get stuck repeating themselves	0%	0.6%

Ability kept (greedy): GSM8K 94.0% (base 70.0%, mostly cut off mid-thought), code with unit tests 84.2% (base 57.9%), tool calling 62.3% (base 59.2%).

Usage

Sampling is already set in generation_config.json (temperature 1.0, top_p 0.95, top_k 64), so you don't need to pass anything. It also holds up at lower temperatures.

vllm serve beyoru/mira-12b --reasoning-parser gemma4 --tool-call-parser gemma4 --enable-auto-tool-choice

from transformers import AutoTokenizer, AutoModelForCausalLM
tok = AutoTokenizer.from_pretrained("beyoru/mira-12b")
model = AutoModelForCausalLM.from_pretrained("beyoru/mira-12b", torch_dtype="bfloat16", device_map="auto")
msgs = [{"role": "user", "content": "long day. my brain is soup"}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, enable_thinking=True, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(ids, max_new_tokens=1024, do_sample=True)[0][ids.shape[1]:]))

Limitations

It can make up specifics when it doesn't know them (song titles, names, rules), so check facts before you rely on them. In about 1% of answers it closes its thinking twice and writes a second version after a stray <channel|>; keeping only the text after the last <channel|> fixes it. Style numbers are automatic counts, not human ratings.

License

Non-commercial use only. The Mira 12B weights, this card and its images are released under CC BY-NC 4.0: you can use, share and adapt the model for research and personal projects with attribution, but you may not use it, or offer it or its outputs as part of a paid product or service, without written permission. For commercial licensing, contact beyoru.

Mira 12B is built on Gemma 4 12B by Google, licensed under the Apache License 2.0; see NOTICE and LICENSE-APACHE-2.0.

Citation

@misc{mira12b2026,
  title        = {Mira 12B: a chat model that talks like a person},
  author       = {beyoru},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/beyoru/mira-12b}},
  note         = {Fine-tuned from Gemma 4 12B}
}

Downloads last month: 16

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for beyoru/mira-12b

Quantizations

2 models