Instructions to use Flashtond22/Taltos-27B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Flashtond22/Taltos-27B-FP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Flashtond22/Taltos-27B-FP8")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Flashtond22/Taltos-27B-FP8")
model = AutoModelForMultimodalLM.from_pretrained("Flashtond22/Taltos-27B-FP8", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Flashtond22/Taltos-27B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Flashtond22/Taltos-27B-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Flashtond22/Taltos-27B-FP8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Flashtond22/Taltos-27B-FP8

SGLang

How to use Flashtond22/Taltos-27B-FP8 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 "Flashtond22/Taltos-27B-FP8" \
    --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": "Flashtond22/Taltos-27B-FP8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Flashtond22/Taltos-27B-FP8" \
        --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": "Flashtond22/Taltos-27B-FP8",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Flashtond22/Taltos-27B-FP8 with Docker Model Runner:
```
docker model run hf.co/Flashtond22/Taltos-27B-FP8
```

✦ TÁLTOS-27B ✦ FP8

A Táltos-27B FP8 kvantált változata

Ez a Táltos-27B FP8 (W8A8) változata: a súlyok csatornánkénti, az aktivációk tokenenkénti dinamikus skálázással. A méret feleződik, a minőségromlás gyakorlatilag mérhetetlen.

Ez a változat akkor kell, ha egyetlen 40 GB körüli kártyán szeretnéd futtatni. L40S, A6000, A100 40 GB, RTX 6000 Ada.

Indítás

vllm serve Flashtond22/Taltos-27B-FP8 \
  --served-model-name taltos \
  --max-model-len 32768 \
  --reasoning-parser qwen3

from openai import OpenAI
client = OpenAI(base_url="http://localhost:8000/v1", api_key="-")

válasz = client.chat.completions.create(
    model="taltos",
    messages=[{"role": "user", "content": "Írj egy udvarias felmondólevelet."}],
)
print(válasz.choices[0].message.content)

Változatok

Változat	Méret	VRAM	Ajánlott hardver
bf16	56 GB	~58 GB	H100, 2 × A100
FP8 (ez)	30 GB	~32 GB	L40S, A6000, A100 40 GB
GGUF	10 GB-tól	12 GB-tól	Ollama, llama.cpp, CPU

A modell leírása, mérési eredményei és használati útmutatója az alap repóban.

✦ TÁLTOS-27B ✦

Magyar fejlesztés

Downloads last month: 37

Safetensors

Model size

28B params

Tensor type

BF16

F8_E4M3

Model tree for Flashtond22/Taltos-27B-FP8

Base model

Qwen/Qwen3.8-27B

Finetuned

Flashtond22/Taltos-27B

Quantized

(3)

this model