Instructions to use Riconec/Holo-3.1-35B-A3B-no-MTP-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 Riconec/Holo-3.1-35B-A3B-no-MTP-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 Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Riconec/Holo-3.1-35B-A3B-no-MTP-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 Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Riconec/Holo-3.1-35B-A3B-no-MTP-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 Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Riconec/Holo-3.1-35B-A3B-no-MTP-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 Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Riconec/Holo-3.1-35B-A3B-no-MTP-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": "Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M

Ollama
How to use Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF with Ollama:
```
ollama run hf.co/Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Riconec/Holo-3.1-35B-A3B-no-MTP-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": "Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M
```

Lemonade

How to use Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Holo-3.1-35B-A3B-no-MTP-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Riconec/Holo-3.1-35B-A3B-no-MTP-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 Riconec/Holo-3.1-35B-A3B-no-MTP-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 Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Riconec/Holo-3.1-35B-A3B-no-MTP-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 "Riconec/Holo-3.1-35B-A3B-no-MTP-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"

Holo-3.1-35B-A3B GGUF Q4_K_M (no MTP)

This repository contains a GGUF conversion of Hcompany/Holo-3-1-35B-A3B for llama.cpp.

Files

holo-3.1-35b-a3b-no-mtp-Q4_K_M.gguf — Q4_K_M quantized GGUF, ~20 GiB

Important note: no MTP

The upstream model config advertises:

"text_config": {
  "num_hidden_layers": 40,
  "mtp_num_hidden_layers": 1
}

However, the published safetensors/index only contain the base layers model.layers.0 through model.layers.39. No model.layers.40 / MTP tensors were found in the downloaded checkpoint.

If converted as-is, llama.cpp expects an extra MTP block and fails to load the GGUF with an error similar to:

missing tensor 'blk.40.attn_norm.weight'

For this conversion, text_config.mtp_num_hidden_layers was set to 0 before conversion. The resulting GGUF is a normal 40-block text model without the built-in MTP head.

Verified GGUF metadata:

general.architecture: qwen35moe
qwen35moe.block_count: 40
qwen35moe.nextn_predict_layers: absent
tensor_count: 733
max block: 39
has blk.40: false

Conversion details

Source model: Hcompany/Holo-3-1-35B-A3B
llama.cpp commit used locally: 5254a79
Conversion: convert_hf_to_gguf.py --outtype f16
Quantization: llama-quantize ... Q4_K_M
F16 intermediate size: 69,376,637,088 bytes
Q4_K_M output size: 21,166,757,728 bytes

Quantization summary:

model size = 66152.24 MiB / 16.01 BPW
quant size = 20175.71 MiB / 4.88 BPW

Example llama.cpp usage

llama-cli \
  -m holo-3.1-35b-a3b-no-mtp-Q4_K_M.gguf \
  -p "Hello" \
  -n 128 \
  -c 4096

For CUDA/P40-style serving, tune for your local build and VRAM budget, for example:

llama-server \
  -m holo-3.1-35b-a3b-no-mtp-Q4_K_M.gguf \
  -c 32768 \
  -ngl 999 \
  -ctk q5_0 \
  -ctv q5_0 \
  --flash-attn \
  --host 0.0.0.0 \
  --port 1235

Disclaimer

This is an unofficial community conversion/quantization. Please refer to the upstream model repository for license, intended use, and model details.

Downloads last month: 19

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

Hcompany/Holo-3.1-35B-A3B

Quantized

(14)

this model

Riconec
/

Holo-3.1-35B-A3B-no-MTP-GGUF

Holo-3.1-35B-A3B GGUF Q4_K_M (no MTP)

Files

Important note: no MTP

Conversion details

Example llama.cpp usage

Disclaimer

Model tree for Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF

Space using Riconec/Holo-3.1-35B-A3B-no-MTP-GGUF 1