Instructions to use bartowski/darkps_ice-AI-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 bartowski/darkps_ice-AI-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 bartowski/darkps_ice-AI-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/darkps_ice-AI-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 bartowski/darkps_ice-AI-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/darkps_ice-AI-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 bartowski/darkps_ice-AI-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/darkps_ice-AI-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 bartowski/darkps_ice-AI-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/darkps_ice-AI-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/darkps_ice-AI-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/darkps_ice-AI-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/darkps_ice-AI-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": "bartowski/darkps_ice-AI-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/darkps_ice-AI-GGUF:Q4_K_M

Ollama
How to use bartowski/darkps_ice-AI-GGUF with Ollama:
```
ollama run hf.co/bartowski/darkps_ice-AI-GGUF:Q4_K_M
```
Unsloth Desktop

How to use bartowski/darkps_ice-AI-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/darkps_ice-AI-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": "bartowski/darkps_ice-AI-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use bartowski/darkps_ice-AI-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/darkps_ice-AI-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/darkps_ice-AI-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/darkps_ice-AI-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.darkps_ice-AI-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use bartowski/darkps_ice-AI-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 bartowski/darkps_ice-AI-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 bartowski/darkps_ice-AI-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bartowski/darkps_ice-AI-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf bartowski/darkps_ice-AI-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 "bartowski/darkps_ice-AI-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"

Llamacpp imatrix Quantizations of ice-AI by darkps

Using llama.cpp release b10665 for quantization.

Original model: https://huggingface.co/darkps/ice-AI

Model details:

Parameter count: 8B
Input support: text
Speculative decoding: no
imatrix: yes - details

How to run

Prompt format

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Don't know which to choose? Grab Q4_K_M (5.20GB) - usually a good mix of size and performance. Download instructions available here

Available files:

Filename	Quant type	File Size	Split	Description
darkps_ice-AI-bf16.gguf	bf16	16.39GB	false	Full BF16 weights.
darkps_ice-AI-Q8_0.gguf	Q8_0	8.71GB	false	Extremely high quality, generally unneeded but max available quant.
darkps_ice-AI-Q6_K_L.gguf	Q6_K_L	7.30GB	false	Uses Q8_0 for embed and output weights. Very high quality, near perfect, recommended.
darkps_ice-AI-Q6_K.gguf	Q6_K	7.00GB	false	Very high quality, near perfect, recommended.
darkps_ice-AI-Q5_K_L.gguf	Q5_K_L	6.38GB	false	Uses Q8_0 for embed and output weights. High quality, recommended.
darkps_ice-AI-Q5_K_M.gguf	Q5_K_M	5.99GB	false	High quality, recommended.
darkps_ice-AI-Q5_K_S.gguf	Q5_K_S	5.76GB	false	High quality, recommended.
darkps_ice-AI-Q4_K_L.gguf	Q4_K_L	5.66GB	false	Uses Q8_0 for embed and output weights. Good quality, recommended.
darkps_ice-AI-Q4_1.gguf	Q4_1	5.31GB	false	Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
darkps_ice-AI-Q4_K_M.gguf	Q4_K_M	5.20GB	false	Good quality, default size for most use cases, recommended.
darkps_ice-AI-Q3_K_XL.gguf	Q3_K_XL	5.02GB	false	Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
darkps_ice-AI-IQ4_NL.gguf	IQ4_NL	4.89GB	false	Similar to IQ4_XS, but slightly larger.
darkps_ice-AI-Q4_K_S.gguf	Q4_K_S	4.89GB	false	Slightly lower quality with more space savings, recommended.
darkps_ice-AI-Q4_0.gguf	Q4_0	4.87GB	false	Legacy format, kept for compatibility with older tools.
darkps_ice-AI-IQ4_XS.gguf	IQ4_XS	4.67GB	false	Decent quality, smaller than Q4_K_S with similar performance, recommended.
darkps_ice-AI-Q3_K_L.gguf	Q3_K_L	4.47GB	false	Lower quality but usable, good for low RAM availability.
darkps_ice-AI-Q3_K_M.gguf	Q3_K_M	4.25GB	false	Low quality.
darkps_ice-AI-Q2_K_L.gguf	Q2_K_L	4.04GB	false	Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
darkps_ice-AI-IQ3_M.gguf	IQ3_M	4.03GB	false	Medium-low quality, new method with decent performance comparable to Q3_K_M.
darkps_ice-AI-Q3_K_S.gguf	Q3_K_S	3.89GB	false	Low quality, not recommended.
darkps_ice-AI-IQ3_XS.gguf	IQ3_XS	3.78GB	false	Lower quality, new method with decent performance, slightly better than Q3_K_S.
darkps_ice-AI-IQ3_XXS.gguf	IQ3_XXS	3.55GB	false	Lower quality, new method with decent performance, comparable to Q3 quants.
darkps_ice-AI-Q2_K.gguf	Q2_K	3.43GB	false	Very low quality but surprisingly usable.
darkps_ice-AI-IQ2_M.gguf	IQ2_M	3.36GB	false	Relatively low quality, uses SOTA techniques to be surprisingly usable.

Download a specific file:

hf download bartowski/darkps_ice-AI-GGUF --include "darkps_ice-AI-Q4_K_M.gguf" --local-dir ./

Downloading using the Hugging Face CLI

Click to view download instructions

First, make sure you have the Hugging Face CLI installed:

pip install -U "huggingface_hub[cli]"

Download a specific file:

hf download bartowski/darkps_ice-AI-GGUF --include "darkps_ice-AI-Q4_K_M.gguf" --local-dir ./

How to run

These quants run with llama.cpp - installable in one line via llama.app:

curl -LsSf https://llama.app/install.sh | sh
llama-server -hf bartowski/darkps_ice-AI-GGUF:Q4_K_M

llama-server includes a built-in chat web UI, served at http://localhost:8080 by default.

These quants were made with llama.cpp release b10665 - if this model's architecture is newly supported, you'll need that release or newer to run them.

They also work in: LM Studio · koboldcpp · ramalama · Jan AI · Text Generation Web UI · LoLLMs · Atomic Chat

imatrix

All quants made using imatrix option, with a calibration corpus rendered through this model's own chat template. The corpus pairs plain prose with tool-calling and reasoning conversations (corpus source data), encoded exactly as this model sees them at inference and processed with --parse-special, so chat-format special tokens contribute to the importance matrix. The corpus rendered for this model is included in this repo: darkps_ice-AI-calibration-v6.txt. The imatrix is available here: darkps_ice-AI-imatrix.gguf.

Calibration render details

{
  "generator": "auto_quant_v2 calibration renderer",
  "recipe": "calibration-v6",
  "model": "ice-AI",
  "encoder": "chat_template",
  "chunk_size": 512,
  "prose_chunks": 218,
  "tool_chunks": 299,
  "total_chunks": 517,
  "tool_chunk_fraction": 0.578,
  "n_conversations": 137,
  "extension_convs_used": 0,
  "conversation_token_lengths": [
    446,
    1498,
    764,
    1268,
    975,
    1218,
    2403,
    524,
    1084,
    1093,
    938,
    1978,
    755,
    831,
    2250,
    1105,
    999,
    867,
    617,
    597,
    1230,
    896,
    1223,
    1082,
    1600,
    1378,
    912,
    581,
    838,
    1369,
    1392,
    695,
    1125,
    918,
    1014,
    1545,
    1497,
    1060,
    359,
    1780,
    1279,
    970,
    1248,
    1645,
    1840,
    1164,
    1491,
    624,
    2276,
    977,
    2510,
    644,
    878,
    618,
    898,
    579,
    2168,
    613,
    1029,
    967,
    1077,
    1048,
    784,
    877,
    821,
    1290,
    782,
    1395,
    1713,
    718,
    321,
    982,
    2888,
    2627,
    591,
    615,
    895,
    662,
    1150,
    955,
    999,
    671,
    917,
    907,
    1167,
    1366,
    1247,
    1235,
    724,
    533,
    2311,
    629,
    1028,
    1539,
    1801,
    1084,
    509,
    1212,
    1119,
    1587,
    1565,
    1509,
    692,
    633,
    895,
    2628,
    621,
    464,
    629,
    1139,
    932,
    1250,
    650,
    349,
    317,
    2166,
    592,
    988,
    1699,
    1564,
    2208,
    2227,
    558,
    858,
    722,
    698,
    1094,
    855,
    727,
    1187,
    711,
    591,
    1286,
    885,
    799,
    1162,
    1322
  ],
  "warnings": []
}

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

ARM/AVX information

llama.cpp automatically "repacks" weights into an interleaved layout at load time for faster inference on ARM and AVX machines - details in this PR. This once required downloading special Q4_0_4_4/4_8/8_8 files; those are long gone. Online repacking now covers Q4_0, IQ4_NL, and most K-quants, so no special quant choice is needed for CPU inference.

Which file should I choose?

Click here for details

An older (early 2024) but still useful write-up with charts comparing quant performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Hugging Face can also do this math for you: add your hardware in your Local Apps settings and the model page will show which files fit.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.