Instructions to use cbert33/NeoHorse-1-9B-FP8-Calibrated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cbert33/NeoHorse-1-9B-FP8-Calibrated with Transformers:

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

pipe = pipeline("text-generation", model="cbert33/NeoHorse-1-9B-FP8-Calibrated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cbert33/NeoHorse-1-9B-FP8-Calibrated")
model = AutoModelForCausalLM.from_pretrained("cbert33/NeoHorse-1-9B-FP8-Calibrated", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cbert33/NeoHorse-1-9B-FP8-Calibrated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cbert33/NeoHorse-1-9B-FP8-Calibrated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cbert33/NeoHorse-1-9B-FP8-Calibrated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cbert33/NeoHorse-1-9B-FP8-Calibrated

SGLang

How to use cbert33/NeoHorse-1-9B-FP8-Calibrated 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 "cbert33/NeoHorse-1-9B-FP8-Calibrated" \
    --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": "cbert33/NeoHorse-1-9B-FP8-Calibrated",
		"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 "cbert33/NeoHorse-1-9B-FP8-Calibrated" \
        --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": "cbert33/NeoHorse-1-9B-FP8-Calibrated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cbert33/NeoHorse-1-9B-FP8-Calibrated with Docker Model Runner:
```
docker model run hf.co/cbert33/NeoHorse-1-9B-FP8-Calibrated
```

NeoHorse-1-9B FP8 Calibrated

NeoHorse is a recent Qwen finetune that we started using and liked. You can find it here: TokenRhythm/NeoHorse-1-9B

This version quantizes both the weights and the cache to FP8 to run on smaller hardware. We kept the FP8 weights at block over dynamic quant for higher quality.

Quantization

FP8 block-scaled weights with 128 x 128 weight blocks
Dynamic grouped FP8 input activations
Static tensor-wise FP8 KV-cache scales calibrated from 512 UltraChat samples
Calibration sequence length: 2,048 tokens
Quantized with LLM Compressor 0.13.0
Serialized with the compressed-tensors format

The embedding table, language-model head, and sensitive hybrid linear-attention state remain in the source precision.

Validation

The packaged validation report records:

643 readable output tensors
200 FP8 weight tensors and 200 matching weight-scale tensors
8 calibrated K-cache scales and 8 calibrated V-cache scales
74 protected tensors that exactly match the source checkpoint
complete SHA-256 checksums for the release files

See VALIDATION_REPORT.json, recipe.yaml, and SHA256SUMS for the recorded artifact checks.

Compatibility

The checkpoint uses the Qwen3.5 text architecture and the compressed-tensors FP8 format. Use a recent runtime that supports both the architecture and FP8 block quantization. Our tests were on vLLM on the DGX Spark.

License

The source model is licensed under Apache 2.0. See the source repository for its model documentation and usage terms.

Downloads last month: 13

Safetensors

Model size

9B params

Tensor type

BF16

F8_E4M3

Model tree for cbert33/NeoHorse-1-9B-FP8-Calibrated

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

TokenRhythm/NeoHorse-1-9B

Quantized

(13)

this model