Instructions to use FINAL-Bench/Darwin-28B-Coder-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 FINAL-Bench/Darwin-28B-Coder-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 FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FINAL-Bench/Darwin-28B-Coder-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 FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use FINAL-Bench/Darwin-28B-Coder-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Darwin-28B-Coder-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": "FINAL-Bench/Darwin-28B-Coder-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M

Ollama
How to use FINAL-Bench/Darwin-28B-Coder-GGUF with Ollama:
```
ollama run hf.co/FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M
```
Unsloth Desktop

How to use FINAL-Bench/Darwin-28B-Coder-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FINAL-Bench/Darwin-28B-Coder-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": "FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use FINAL-Bench/Darwin-28B-Coder-GGUF with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M
```

Lemonade

How to use FINAL-Bench/Darwin-28B-Coder-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Darwin-28B-Coder-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use FINAL-Bench/Darwin-28B-Coder-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 FINAL-Bench/Darwin-28B-Coder-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 FINAL-Bench/Darwin-28B-Coder-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use FINAL-Bench/Darwin-28B-Coder-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FINAL-Bench/Darwin-28B-Coder-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 "FINAL-Bench/Darwin-28B-Coder-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"

Darwin-28B-Coder-GGUF / README.md

SeaWolf-AI

card: add insights cross-links (on-device / quantization)

ef8ab14 verified 3 months ago

preview code

Raw History Blame Contribute Delete

4.14 kB

metadata

license: apache-2.0
base_model: FINAL-Bench/Darwin-28B-Coder
base_model_relation: quantized
library_name: gguf
pipeline_tag: text-generation
tags:
  - gguf
  - llama.cpp
  - mtp
  - multi-token-prediction
  - speculative-decoding
  - code
language:
  - en
  - ko

📱 Run it on your phone or a GPU-less PC → POCKET · 🚀 Try it live (CPU chat)

VIDRAFT's on-device family: a 35B model that runs on iPhone and on CPU with no GPU — stock llama.cpp, no fork.

Darwin-28B-Coder — GGUF (MTP-enabled)

GGUF builds of FINAL-Bench/Darwin-28B-Coder with the native Multi-Token Prediction (MTP) head preserved, for self-speculative decoding in llama.cpp.

Requested in the base model discussion.

Files

File	Quant	Size	Notes
`Darwin-28B-Coder-Q4_K_M.gguf`	Q4_K_M	16.8 GB	recommended for most GPUs
`Darwin-28B-Coder-Q8_0.gguf`	Q8_0	29.0 GB	near-lossless
`Darwin-28B-Coder-F16.gguf`	F16	54.7 GB	full precision

All files include the MTP layer — verified in metadata: general.architecture = qwen35, qwen35.nextn_predict_layers = 1, tensors blk.64.nextn.*.

Multi-Token Prediction (MTP)

This model ships with a trained MTP head (1 prediction layer). With a recent llama.cpp build that includes MTP support (merged in PR #22673), the nextn layer is used for self-speculative decoding — typically ~1.5–2× faster generation with identical output (the main model verifies every drafted token, so quality is unchanged).

A standard (non-MTP) GGUF does not contain the prediction head — you need these MTP-enabled files to benefit from the speedup.

Usage

# 1) Build a recent llama.cpp (MTP support is in mainline since PR #22673)
git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp
cmake -B build -DGGML_CUDA=ON && cmake --build build -j --config Release

# 2) Run — the nextn (MTP) layer enables self-speculative decoding
./build/bin/llama-cli \
  -m Darwin-28B-Coder-Q4_K_M.gguf \
  -ngl 99 -c 8192 \
  -p "Write a quicksort in Python."

For the exact MTP/speculative flags and the latest behaviour, see the llama.cpp MTP documentation / PR #22673. Works with llama-cli and llama-server.

Model spec (public)


Architecture	`qwen35` (hybrid attention)
Layers	64 + 1 MTP
Hidden size	5120
Attention heads	24 (KV 4)
Context length	262,144
Vocab	248,320
Precision (source)	bfloat16

License & attribution

License and usage follow the base model FINAL-Bench/Darwin-28B-Coder. These are GGUF conversions only; refer to the base model card for model details, intended use, and limitations.

GGUF conversion + quantization by the FINAL-Bench team using llama.cpp/convert_hf_to_gguf.py.

Learn more

Running large coding models on-device without a GPU: Can you run a large LLM without a GPU?
What model quantization is: What is model quantization?

FINAL-Bench
/

Darwin-28B-Coder-GGUF

📱 Run it on your phone or a GPU-less PC → POCKET · 🚀 Try it live (CPU chat)

Darwin-28B-Coder — GGUF (MTP-enabled)

Files

Multi-Token Prediction (MTP)

Usage

Model spec (public)

License & attribution

Learn more