Instructions to use elsauto/tosilos-128b-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 elsauto/tosilos-128b-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 elsauto/tosilos-128b-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf elsauto/tosilos-128b-GGUF:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf elsauto/tosilos-128b-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf elsauto/tosilos-128b-GGUF:Q3_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 elsauto/tosilos-128b-GGUF:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf elsauto/tosilos-128b-GGUF:Q3_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 elsauto/tosilos-128b-GGUF:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf elsauto/tosilos-128b-GGUF:Q3_K_M

Use Docker

docker model run hf.co/elsauto/tosilos-128b-GGUF:Q3_K_M

LM Studio
Jan

vLLM

How to use elsauto/tosilos-128b-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/elsauto/tosilos-128b-GGUF:Q3_K_M

Ollama
How to use elsauto/tosilos-128b-GGUF with Ollama:
```
ollama run hf.co/elsauto/tosilos-128b-GGUF:Q3_K_M
```

Unsloth Studio

How to use elsauto/tosilos-128b-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 elsauto/tosilos-128b-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 elsauto/tosilos-128b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for elsauto/tosilos-128b-GGUF to start chatting

How to use elsauto/tosilos-128b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf elsauto/tosilos-128b-GGUF:Q3_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": "elsauto/tosilos-128b-GGUF:Q3_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use elsauto/tosilos-128b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf elsauto/tosilos-128b-GGUF:Q3_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 "elsauto/tosilos-128b-GGUF:Q3_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"

Docker Model Runner
How to use elsauto/tosilos-128b-GGUF with Docker Model Runner:
```
docker model run hf.co/elsauto/tosilos-128b-GGUF:Q3_K_M
```

Lemonade

How to use elsauto/tosilos-128b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull elsauto/tosilos-128b-GGUF:Q3_K_M

Run and chat with the model

lemonade run user.tosilos-128b-GGUF-Q3_K_M

List all available models

lemonade list

Hermes Agent

How to use elsauto/tosilos-128b-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 elsauto/tosilos-128b-GGUF:Q3_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 elsauto/tosilos-128b-GGUF:Q3_K_M

Run Hermes

hermes

Atomic Chat

Tosilos-128B GGUF

Community GGUF conversion and quantization of nesilabs/tosilos-128b for use with llama.cpp.

The original model is a Mistral Medium 3.5 128B cybersecurity fine-tune intended for authorized pentesting, vulnerability analysis, DFIR, detection engineering, and related cybersecurity workflows, as described by Nesilabs.

Original model: nesilabs/tosilos-128b

This repository contains a community-produced GGUF conversion/quantization. It is not a retrained or independently fine-tuned model. All credit for the original model and fine-tuning belongs to Nesilabs and the original model authors.

Available quantization

File	Quantization	BPW	Approx. size
`tosilos-128b-Q3_K_M.gguf`	Q3_K_M	3.88	~60.6 GB / ~56.4 GiB

Q3_K_M was selected as a practical starting point for running this dense 128B model on systems with approximately 128 GB of unified/system memory.

Conversion

Converted from the original BF16 Safetensors checkpoint using llama.cpp.

Conversion environment

Source: nesilabs/tosilos-128b
Source format: BF16 Safetensors
llama.cpp build: 10398
llama.cpp commit: 8e7f22b67
Intermediate format: BF16 GGUF
Final quantization: Q3_K_M
Tokenizer compatibility: Transformers 5.15.0 was used successfully for conversion

The conversion pipeline was:

nesilabs/tosilos-128b
        |
        | BF16 Safetensors
        v
convert_hf_to_gguf.py
        |
        v
tosilos-128b-BF16.gguf
        |
        | llama-quantize Q3_K_M
        v
tosilos-128b-Q3_K_M.gguf

Reproducible conversion commands

python3 convert_hf_to_gguf.py \
  /path/to/tosilos-128b \
  --outfile tosilos-128b-BF16.gguf \
  --outtype bf16

llama-quantize \
  tosilos-128b-BF16.gguf \
  tosilos-128b-Q3_K_M.gguf \
  Q3_K_M

For this checkpoint, upgrading the conversion environment to Transformers 5.15.0 resolved tokenizer compatibility with the model's TokenizersBackend metadata.

Tested hardware

The Q3_K_M GGUF has been tested successfully with llama.cpp using Vulkan on:

CPU/APU: AMD Ryzen AI MAX+ 395
GPU: AMD Radeon 8060S Graphics
Memory: 128 GB unified/system memory
Backend: Vulkan
Operating system: Ubuntu Linux

Test configuration

Context: 32768
KV cache: Q8_0
GPU layers: 999 / full layer offload
Batch size: 512
Micro-batch size: 256
Parallel sequences: 1

Observed decode performance was approximately 3.7 tokens/second at a configured 32K context.

Performance will vary depending on hardware, memory bandwidth, context utilization, llama.cpp version, and runtime configuration.

Download

Using the Hugging Face CLI:

hf download elsauto/tosilos-128b-GGUF \
  tosilos-128b-Q3_K_M.gguf \
  --local-dir .

Usage with llama.cpp

llama-server \
  -m ./tosilos-128b-Q3_K_M.gguf \
  -c 32768 \
  -ngl 999 \
  -b 512 \
  -ub 256 \
  --cache-type-k q8_0 \
  --cache-type-v q8_0

For systems with less available GPU or unified memory, reduce GPU offload and/or context size as necessary.

llama.cpp `models.ini` example

[tosilos-128b]
model = /models/tosilos-128b-Q3_K_M.gguf
ctx-size = 32768

n-gpu-layers = 999
batch-size = 512
ubatch-size = 256
parallel = 1

cache-type-k = q8_0
cache-type-v = q8_0

jinja = true
flash-attn = auto

temp = 0.3
top-p = 0.9
top-k = 20
repeat-penalty = 1.05

Intended use

This GGUF preserves the intended use of the original Tosilos-128B model. Refer to the upstream model card for the authoritative description of intended uses, limitations, training information, and model-specific guidance:

nesilabs/tosilos-128b

This repository documents only the GGUF conversion, quantization, and tested llama.cpp configuration.

Attribution

This repository is a community-produced GGUF conversion of:

nesilabs/tosilos-128b

Please credit and refer to the original repository for information about the underlying model.

License

This GGUF is a quantized derivative of the original model. The original model's license and usage terms continue to apply.

Before using or redistributing this GGUF, review the license and terms published by Nesilabs in the original repository:

nesilabs/tosilos-128b

This repository does not grant additional rights beyond those provided by the original model's license.

Downloads last month: 63

GGUF

Model size

125B params

Architecture

mistral3

Hardware compatibility

3-bit

Model tree for elsauto/tosilos-128b-GGUF

Base model

mistralai/Mistral-Medium-3.5-128B

Quantized

nesilabs/tosilos-128b

Quantized

(1)

this model

Tosilos-128B GGUF

Available quantization

Conversion

Conversion environment

Reproducible conversion commands

Tested hardware

Test configuration

Download

Usage with llama.cpp

llama.cpp models.ini example

Intended use

Attribution

License

Model tree for elsauto/tosilos-128b-GGUF

llama.cpp `models.ini` example