Instructions to use HCHs/RivetCoder-9B-A4B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HCHs/RivetCoder-9B-A4B-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="HCHs/RivetCoder-9B-A4B-FP8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("HCHs/RivetCoder-9B-A4B-FP8", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HCHs/RivetCoder-9B-A4B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HCHs/RivetCoder-9B-A4B-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": "HCHs/RivetCoder-9B-A4B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HCHs/RivetCoder-9B-A4B-FP8

SGLang

How to use HCHs/RivetCoder-9B-A4B-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 "HCHs/RivetCoder-9B-A4B-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": "HCHs/RivetCoder-9B-A4B-FP8",
		"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 "HCHs/RivetCoder-9B-A4B-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": "HCHs/RivetCoder-9B-A4B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HCHs/RivetCoder-9B-A4B-FP8 with Docker Model Runner:
```
docker model run hf.co/HCHs/RivetCoder-9B-A4B-FP8
```

RivetCoder-9B-A4B-FP8 / provenance /quantization.json

HCHs

Add Triton grouped-FP8 runtime and microbatch server

a92180d verified about 16 hours ago

Raw

History Blame Contribute Delete

1.76 kB

	{
	"schema": "rivetcoder-fp8-quantization",
	"schema_version": 1,
	"created_at": "2026-08-27T23:01:09+09:00",
	"source": {
	"repo_id": "HCHs/RivetCoder-9B-A4B",
	"revision": "9a90b1917d9b5438e4d2fe1a4f6aea884db59a60"
	},
	"target": {
	"repo_id": "HCHs/RivetCoder-9B-A4B-FP8",
	"local_directory": "RivetCoder-9B-A4B-FP8"
	},
	"method": {
	"framework": "TorchAO",
	"config": "Float8DynamicActivationFloat8WeightConfig",
	"weight_dtype": "float8_e4m3fn",
	"activation_dtype": "float8_e4m3fn",
	"activation_scheme": "dynamic",
	"granularity": "per-tensor",
	"compatible_linear_modules_only": true
	},
	"runtime": {
	"platform": "Windows 11",
	"python": "3.12.10",
	"torch": "2.12.0+cu130",
	"transformers": "5.16.1",
	"accelerate": "1.13.0",
	"safetensors": "0.8.0",
	"torchao": "0.15.0",
	"gpu": "NVIDIA GeForce RTX 5070 Ti",
	"compute_capability": [12, 0]
	},
	"results": {
	"parameter_tensors": 1826,
	"fp8_tensor_subclass_parameters": 1636,
	"fp8_parameter_elements": 8475574272,
	"stored_tensor_bytes": 9000638976,
	"safetensors_shards": 5,
	"all_parameters_materialized": true,
	"all_parameters_on_cuda": true,
	"clean_reload_success": true,
	"clean_reload_seconds": 338.0,
	"clean_reload_fp8_parameters": 1636,
	"clean_reload_non_cuda_parameters": 0,
	"fast_serving_validated": true,
	"fast_serving_logits_bit_exact": true,
	"resident_cuda_allocated_bytes": 9039455232,
	"forward_finite": true,
	"forward_logits_shape": [1, 6, 128000]
	},
	"compatibility": {
	"required_context": "torch.no_grad",
	"known_incompatible_context": "torch.inference_mode",
	"known_error": "Cannot set version_counter for inference tensor"
	}
	}