Instructions to use bartowski/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/TheDrummer_Behemoth-128B-v3-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M

Ollama
How to use bartowski/TheDrummer_Behemoth-128B-v3-GGUF with Ollama:
```
ollama run hf.co/bartowski/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/TheDrummer_Behemoth-128B-v3-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for bartowski/TheDrummer_Behemoth-128B-v3-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for bartowski/TheDrummer_Behemoth-128B-v3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/TheDrummer_Behemoth-128B-v3-GGUF to start chatting

How to use bartowski/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/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/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use bartowski/TheDrummer_Behemoth-128B-v3-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/TheDrummer_Behemoth-128B-v3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.TheDrummer_Behemoth-128B-v3-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use bartowski/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use bartowski/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-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/TheDrummer_Behemoth-128B-v3-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 Behemoth-128B-v3 by TheDrummer

Using llama.cpp release b10472 for quantization.

Original model: https://huggingface.co/TheDrummer/Behemoth-128B-v3

Model details:

Parameter count: 125B
Input support: text
Speculative decoding: no
imatrix: yes - details
Perplexity/KLD measured: no

How to run

Prompt format

<s>[SYSTEM_PROMPT]{system_prompt}[/SYSTEM_PROMPT][MODEL_SETTINGS]{"reasoning_effort": "none"}[/MODEL_SETTINGS][INST]{prompt}[/INST]

Don't know which to choose? Grab Q4_K_M (78.41GB) - usually a good mix of size and performance. Download instructions available here

Available files:

Filename	Quant type	File Size	Split	Description
TheDrummer_Behemoth-128B-v3-bf16.gguf	bf16	250.06GB	true	Full BF16 weights.
TheDrummer_Behemoth-128B-v3-Q8_0.gguf	Q8_0	132.85GB	true	Extremely high quality, generally unneeded but max available quant.
TheDrummer_Behemoth-128B-v3-Q6_K.gguf	Q6_K	107.80GB	true	Very high quality, near perfect, recommended.
TheDrummer_Behemoth-128B-v3-Q5_K_L.gguf	Q5_K_L	92.11GB	true	Uses Q8_0 for embed and output weights. High quality, recommended.
TheDrummer_Behemoth-128B-v3-Q5_K_M.gguf	Q5_K_M	91.11GB	true	High quality, recommended.
TheDrummer_Behemoth-128B-v3-Q5_K_S.gguf	Q5_K_S	87.07GB	true	High quality, recommended.
TheDrummer_Behemoth-128B-v3-Q4_1.gguf	Q4_1	79.77GB	true	Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon.
TheDrummer_Behemoth-128B-v3-Q4_K_L.gguf	Q4_K_L	79.60GB	true	Uses Q8_0 for embed and output weights. Good quality, recommended.
TheDrummer_Behemoth-128B-v3-Q4_K_M.gguf	Q4_K_M	78.41GB	true	Good quality, default size for most use cases, recommended.
TheDrummer_Behemoth-128B-v3-Q4_K_S.gguf	Q4_K_S	73.02GB	true	Slightly lower quality with more space savings, recommended.
TheDrummer_Behemoth-128B-v3-IQ4_NL.gguf	IQ4_NL	72.76GB	true	Similar to IQ4_XS, but slightly larger.
TheDrummer_Behemoth-128B-v3-Q4_0.gguf	Q4_0	72.71GB	true	Legacy format, kept for compatibility with older tools.
TheDrummer_Behemoth-128B-v3-IQ4_XS.gguf	IQ4_XS	69.14GB	true	Decent quality, smaller than Q4_K_S with similar performance, recommended.
TheDrummer_Behemoth-128B-v3-Q3_K_XL.gguf	Q3_K_XL	68.41GB	true	Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability.
TheDrummer_Behemoth-128B-v3-Q3_K_L.gguf	Q3_K_L	67.01GB	true	Lower quality but usable, good for low RAM availability.
TheDrummer_Behemoth-128B-v3-Q3_K_M.gguf	Q3_K_M	63.28GB	true	Low quality.
TheDrummer_Behemoth-128B-v3-IQ3_M.gguf	IQ3_M	59.53GB	true	Medium-low quality, new method with decent performance comparable to Q3_K_M.
TheDrummer_Behemoth-128B-v3-Q3_K_S.gguf	Q3_K_S	56.96GB	true	Low quality, not recommended.
TheDrummer_Behemoth-128B-v3-IQ3_XS.gguf	IQ3_XS	54.93GB	true	Lower quality, new method with decent performance, slightly better than Q3_K_S.
TheDrummer_Behemoth-128B-v3-IQ3_XXS.gguf	IQ3_XXS	52.17GB	false	Lower quality, new method with decent performance, comparable to Q3 quants.
TheDrummer_Behemoth-128B-v3-Q2_K_L.gguf	Q2_K_L	51.43GB	false	Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable.
TheDrummer_Behemoth-128B-v3-Q2_K.gguf	Q2_K	49.86GB	false	Very low quality but surprisingly usable.
TheDrummer_Behemoth-128B-v3-IQ2_M.gguf	IQ2_M	48.61GB	false	Relatively low quality, uses SOTA techniques to be surprisingly usable.
TheDrummer_Behemoth-128B-v3-IQ2_S.gguf	IQ2_S	46.07GB	false	Low quality, uses SOTA techniques to be usable.
TheDrummer_Behemoth-128B-v3-IQ2_XS.gguf	IQ2_XS	43.39GB	false	Low quality, uses SOTA techniques to be usable.
TheDrummer_Behemoth-128B-v3-IQ2_XXS.gguf	IQ2_XXS	40.43GB	false	Very low quality, uses SOTA techniques to be usable.
TheDrummer_Behemoth-128B-v3-IQ1_M.gguf	IQ1_M	37.25GB	false	Extremely low quality, not recommended.
TheDrummer_Behemoth-128B-v3-IQ1_S.gguf	IQ1_S	35.34GB	false	Extremely low quality, not recommended.

Download a specific file:

hf download bartowski/TheDrummer_Behemoth-128B-v3-GGUF --include "TheDrummer_Behemoth-128B-v3-Q4_K_M/*" --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/TheDrummer_Behemoth-128B-v3-GGUF --include "TheDrummer_Behemoth-128B-v3-Q4_K_M/*" --local-dir ./

The files marked true in the Split column above are stored as multiple parts in a folder. To download all the parts to a local folder, run:

hf download bartowski/TheDrummer_Behemoth-128B-v3-GGUF --include "TheDrummer_Behemoth-128B-v3-Q8_0/*" --local-dir ./

You can either specify a new local-dir (TheDrummer_Behemoth-128B-v3-Q8_0) or download them all in place (./)

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/TheDrummer_Behemoth-128B-v3-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 b10472 - 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: TheDrummer_Behemoth-128B-v3-calibration-v6.txt. The imatrix is available here: TheDrummer_Behemoth-128B-v3-imatrix.gguf.

Calibration render details

{
  "generator": "auto_quant_v2 calibration renderer",
  "recipe": "calibration-v6",
  "model": "Behemoth-128B-v3",
  "encoder": "chat_template",
  "chunk_size": 512,
  "prose_chunks": 222,
  "tool_chunks": 395,
  "total_chunks": 617,
  "tool_chunk_fraction": 0.64,
  "n_conversations": 137,
  "extension_convs_used": 0,
  "conversation_token_lengths": [
    721,
    1795,
    1336,
    1633,
    1224,
    1485,
    3267,
    904,
    1333,
    1504,
    1228,
    2270,
    1035,
    1346,
    2902,
    1394,
    1286,
    1146,
    893,
    868,
    1510,
    1139,
    1465,
    1374,
    2006,
    1672,
    1750,
    991,
    1529,
    1762,
    1658,
    1298,
    1396,
    1206,
    1423,
    1812,
    1782,
    1342,
    631,
    2103,
    1591,
    1235,
    1546,
    2141,
    2243,
    1400,
    1794,
    982,
    3057,
    1274,
    3012,
    919,
    1123,
    1073,
    1270,
    854,
    2609,
    989,
    1304,
    1247,
    1308,
    1328,
    1010,
    1320,
    1268,
    1694,
    1040,
    1671,
    2263,
    995,
    682,
    1249,
    3533,
    3006,
    867,
    1014,
    1129,
    1176,
    1396,
    1256,
    1254,
    947,
    1300,
    1162,
    1444,
    1616,
    1543,
    2134,
    999,
    798,
    2854,
    989,
    1509,
    1822,
    2122,
    1371,
    778,
    1505,
    1467,
    1851,
    2013,
    1797,
    988,
    1112,
    1174,
    2925,
    899,
    829,
    914,
    1529,
    1212,
    1715,
    932,
    705,
    669,
    2705,
    1118,
    1261,
    1977,
    2133,
    2796,
    2788,
    913,
    1134,
    996,
    1027,
    1357,
    1126,
    1011,
    1458,
    998,
    867,
    1846,
    1159,
    1082,
    1407,
    1605
  ],
  "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.