Instructions to use rodrigoramosrs/veriloop-coder-e2-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rodrigoramosrs/veriloop-coder-e2-gguf with Transformers:

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

pipe = pipeline("text-generation", model="rodrigoramosrs/veriloop-coder-e2-gguf")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rodrigoramosrs/veriloop-coder-e2-gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use rodrigoramosrs/veriloop-coder-e2-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 rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rodrigoramosrs/veriloop-coder-e2-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 rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rodrigoramosrs/veriloop-coder-e2-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 rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf rodrigoramosrs/veriloop-coder-e2-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 rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M

Use Docker

docker model run hf.co/rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use rodrigoramosrs/veriloop-coder-e2-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rodrigoramosrs/veriloop-coder-e2-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": "rodrigoramosrs/veriloop-coder-e2-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M

SGLang

How to use rodrigoramosrs/veriloop-coder-e2-gguf 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 "rodrigoramosrs/veriloop-coder-e2-gguf" \
    --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": "rodrigoramosrs/veriloop-coder-e2-gguf",
		"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 "rodrigoramosrs/veriloop-coder-e2-gguf" \
        --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": "rodrigoramosrs/veriloop-coder-e2-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use rodrigoramosrs/veriloop-coder-e2-gguf with Ollama:
```
ollama run hf.co/rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M
```
Unsloth Desktop

How to use rodrigoramosrs/veriloop-coder-e2-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rodrigoramosrs/veriloop-coder-e2-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": "rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use rodrigoramosrs/veriloop-coder-e2-gguf with Docker Model Runner:
```
docker model run hf.co/rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M
```

Lemonade

How to use rodrigoramosrs/veriloop-coder-e2-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M

Run and chat with the model

lemonade run user.veriloop-coder-e2-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use rodrigoramosrs/veriloop-coder-e2-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 rodrigoramosrs/veriloop-coder-e2-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 rodrigoramosrs/veriloop-coder-e2-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use rodrigoramosrs/veriloop-coder-e2-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf rodrigoramosrs/veriloop-coder-e2-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 "rodrigoramosrs/veriloop-coder-e2-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"

rodrigoramosrs commited on 17 days ago

Commit

b76868f

verified ·

1 Parent(s): ac4c7ba

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +2 -7

README.md CHANGED Viewed

@@ -56,14 +56,9 @@ Quantized by [Rodrigo Ramos](https://github.com/rodrigoramosrs).
 ## Quantization Approach
-All quants were produced with [llama.cpp](https://github.com/ggml-org/llama.cpp) using a **code-specialized importance matrix (imatrix)** (`Qwen3.8-27B-imatrix.gguf`, same Qwen3.8-27B family — 100% of quantizable tensors covered, verified per-tensor). Unlike generic imatrix datasets, this one preserves fidelity on the distributions that matter most for coding tasks: repository-level code, patches, test suites, and agentic coding traces.
-The result is a set of GGUF files that retain the original model's strong software-engineering capabilities while being deployable via `llama.cpp`, `llama-cpp-python`, `Ollama`, `LM Studio`, and other GGUF-compatible runtimes (use a recent build with QWEN35 + MTP support, e.g. `ik_llama.cpp`).
-Notes:
-- The 34 `mtp.veriloop_engram_registry.*` tensors from the source checkpoint are **not model weights** (embedded data blobs: zips, JSONs, semantic keys — 92 MB total) and are excluded from these GGUFs. The source model's own serving contract ignores that namespace as well.
-- `IQ3_XS` keeps the MTP draft block (`blk.64`) at `Q8_0` for speculative-decoding quality.
 ## Available Quants

 ## Quantization Approach
+All quants were produced with [llama.cpp](https://github.com/ggml-org/llama.cpp) using a **code-specialized importance matrix (imatrix)**. Unlike generic imatrix datasets, this one was curated from software engineering corpora — repository-level code, patches, test suites, and agentic coding traces — ensuring that quantization preserves fidelity on the distributions that matter most for coding tasks.
+The result is a set of GGUF files that retain the original model's strong software-engineering capabilities while being deployable via `llama.cpp`, `llama-cpp-python`, `Ollama`, `LM Studio`, and other GGUF-compatible runtimes.
 ## Available Quants