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 /fast-serving.json

HCHs

Accelerate remaining FP8 linears with direct scaled-mm

4d29b4b verified about 16 hours ago

Raw

History Blame Contribute Delete

1.79 kB

	{
	"schema": "rivetcoder-fast-fp8-serving",
	"schema_version": 1,
	"created_at": "2026-08-27T23:51:49+09:00",
	"hardware": {
	"gpu": "NVIDIA GeForce RTX 5070 Ti",
	"compute_capability": [12, 0],
	"vram_mib": 16303
	},
	"software": {
	"platform": "Windows 11",
	"python": "3.12.10",
	"torch": "2.12.0+cu130",
	"torchao": "0.15.0",
	"transformers": "5.16.1",
	"triton": "3.5.1",
	"compiler": "MSVC 19.44.35222"
	},
	"implementation": {
	"backend": "Triton grouped FP8",
	"packed_layers": 30,
	"packed_experts": 480,
	"direct_fp8_linears": 196,
	"top_k": 4,
	"expert_gemms_per_layer": 2,
	"gate_up_shape": [16, 4096, 2048],
	"down_shape": [16, 2048, 2048],
	"activation_scaling": "dynamic per routed expert",
	"weight_scaling": "checkpoint-preserving per projection",
	"kernel_reference": "kernels-community/finegrained-fp8",
	"kernel_license": "Apache-2.0"
	},
	"full_model_parity": {
	"baseline_seconds": 4.8937,
	"fast_seconds": 0.3044,
	"speedup": 16.08,
	"mean_absolute_logit_error": 0.0,
	"maximum_absolute_logit_error": 0.0,
	"top1_equal": true,
	"repeat_maximum_absolute_error": 0.0,
	"resident_vram_gib": 8.428,
	"packing_peak_vram_gib": 14.053
	},
	"microbatch_forward": [
	{"batch": 1, "seconds": 0.3374, "sequences_per_second": 2.9635},
	{"batch": 4, "seconds": 0.3162, "sequences_per_second": 12.6488},
	{"batch": 8, "seconds": 0.3404, "sequences_per_second": 23.5045},
	{"batch": 16, "seconds": 0.3094, "sequences_per_second": 51.7069}
	],
	"server": {
	"protocol": "OpenAI-compatible chat completions",
	"batching": "queue-to-completion fixed microbatch",
	"default_max_batch_size": 16,
	"default_batch_wait_ms": 3.0,
	"streaming": false
	}
	}