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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use HCHs/RivetCoder-9B-A4B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

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

Use Docker

docker model run hf.co/HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

Ollama
How to use HCHs/RivetCoder-9B-A4B-GGUF with Ollama:
```
ollama run hf.co/HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M
```
Unsloth Desktop

How to use HCHs/RivetCoder-9B-A4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use HCHs/RivetCoder-9B-A4B-GGUF with Docker Model Runner:
```
docker model run hf.co/HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M
```

Lemonade

How to use HCHs/RivetCoder-9B-A4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.RivetCoder-9B-A4B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use HCHs/RivetCoder-9B-A4B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use HCHs/RivetCoder-9B-A4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "HCHs/RivetCoder-9B-A4B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

RivetCoder-9B-A4B-GGUF / VALIDATION.md

HCHs

Add Q8_0 and Q4_K_M GGUF quantizations with custom llama.cpp runtime

e57b37d verified about 14 hours ago

preview code

Raw

History Blame Contribute Delete

3.03 kB

Runtime validation

This release was gated on successful loading, server startup, and real token generation. It was not gated on coding-answer quality.

Structural checks

Run from the release workspace root:

$Python = '.\.venv\Scripts\python.exe'
$Validator = '.\tools\validate_rivetcoder_gguf.py'
$Llama = '.\work\llama.cpp-rivetcoder'
$Source = '.\RivetCoder-9B-A4B'
$Package = '.\RivetCoder-9B-A4B-GGUF'

& $Python $Validator "$Package\RivetCoder-9B-A4B-Q8_0.gguf" `
  --llama-cpp-dir $Llama `
  --hf-model $Source `
  --expected-file-type Q8_0 `
  --strict-extra-tensors `
  --report "$Package\provenance\q8-structure.json"

& $Python $Validator "$Package\RivetCoder-9B-A4B-Q4_K_M.gguf" `
  --llama-cpp-dir $Llama `
  --hf-model $Source `
  --expected-file-type Q4_K_M `
  --strict-extra-tensors `
  --report "$Package\provenance\q4km-structure.json"

Both reports must contain "ok": true, 506 tensors, no missing or extra tensors, no warnings, and zero routing-control mismatches.

CLI generation check

After extracting bundle/rivetcoder-llama-windows-cuda-sm120.zip:

.\llama-cli.exe `
  --model .\RivetCoder-9B-A4B-Q4_K_M.gguf `
  --n-gpu-layers all `
  --ctx-size 512 `
  --batch-size 64 `
  --ubatch-size 64 `
  --predict 16 `
  --prompt 'Reply with OK only.' `
  --temperature 0 `
  --single-turn `
  --simple-io `
  --no-warmup `
  --perf

Success requires model load, at least one generated token, and process exit code 0. Repeat with the Q8_0 file.

Server check

$server = Start-Process `
  -FilePath '.\llama-server.exe' `
  -ArgumentList @(
    '--model', '.\RivetCoder-9B-A4B-Q4_K_M.gguf',
    '--alias', 'RivetCoder-9B-A4B',
    '--host', '127.0.0.1',
    '--port', '8080',
    '--n-gpu-layers', 'all',
    '--ctx-size', '4096',
    '--parallel', '1',
    '--batch-size', '512',
    '--ubatch-size', '256',
    '--flash-attn', 'on',
    '--reasoning-budget', '0'
  ) `
  -PassThru `
  -WindowStyle Hidden

Invoke-RestMethod http://127.0.0.1:8080/health

$body = @{
  model = 'RivetCoder-9B-A4B'
  messages = @(@{ role = 'user'; content = 'Say OK.' })
  temperature = 0
  max_tokens = 16
} | ConvertTo-Json -Depth 8

Invoke-RestMethod `
  -Method Post `
  -Uri http://127.0.0.1:8080/v1/chat/completions `
  -ContentType application/json `
  -Body $body

Stop-Process -Id $server.Id

Success requires GET /health to return {"status":"ok"}, a non-error completion response containing generated tokens, and no CUDA/graph/tensor errors in the server log.

Recorded results

Artifact	Load/generate	Structure	SHA-256
BF16 conversion	pass, exit 0	pass	`f51dfc1cb82b281156a09360bdbe8fe95734334e01d0d6b6c2df4a27b2619aea`
Q8_0	pass, exit 0	pass	`6e71dd349df93f734b89fd70f2d0590037ddd3bdc11a4e9533991a0eab47b85e`
Q4_K_M	pass, exit 0	pass	`980adc81f64b52bc71228abd0e2bed02a1b6a00bdda9afbfd6d5e0c124ac5600`

The BF16 intermediate is intentionally not part of the public quantized release.