Instructions to use IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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 IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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 IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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 IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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 IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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 IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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": "IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M

Ollama
How to use IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF with Ollama:
```
ollama run hf.co/IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M
```
Unsloth Desktop

How to use IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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": "IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF with Docker Model Runner:
```
docker model run hf.co/IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M
```

Lemonade

How to use IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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 IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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 IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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 "IsValorum/MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1-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"

Quick Navigation Index

Independent Community Benchmarks (Shortbench / NanoBench v0.5.0)
Key Architectural Features
CLI Usage Example

Independently computed using dedicated cloud compute clusters, funded 100% out-of-pocket.

If you consider these releases to be of high quality and they help you in your day-to-day workflow, consider supporting on Ko-fi. Every contribution directly sustains future cloud compute hours and helps support my university studies.

🏅 Independent Community Benchmarks (Shortbench / NanoBench v0.5.0)

Verified Autonomous Agent Evaluation: Evaluated on the Shortbench / NanoBench v0.5.0 autonomous coding and agentic benchmark (12 objective software engineering, pipeline, and system integrity tasks).

In independent testing conducted by community member @derFusel on a consumer NVIDIA GeForce RTX 4070 (12 GB VRAM) workstation, MiniCPM-V-4.7-35B-A3B-APEX-I-MiniPlus-V2.1 demonstrated strong agentic and tool execution speeds:

Benchmark Run	Total Score	Solved Tasks	Completion Time	Tested Hardware & Environment	Public Verification Link
MiniCPM-V-4.7 MiniPlus (Compacted)	95.8%	10 / 12	7.60 min	RTX 4070 (12GB) / i7-14700K / 32GB RAM (`Pi` Agent, compacted)	Verified Run 2a1b0ff3
MiniCPM-V-4.7 MiniPlus	89.6%	8 / 12	6.50 min	RTX 4070 (12GB) / i7-14700K / 32GB RAM (`Pi` Agent)	Verified Run 9fe7781b

Key Empirical Takeaways:

Blistering Execution Speed (6.5 – 7.6 min): The fastest completion time recorded among 35B models evaluated on Shortbench, reflecting ultra-low latency in generating structured tool and Python payloads.
Multimodal MoE Precision: Proves that MiniCPM-V 4.7's hybrid MoE vision architecture retains high coding fidelity and tool invocation capabilities when quantized with APEX-I MiniPlus.

MiniCPM-V 4.7 35B-A3B APEX-I MiniPlus V2.1 GGUF

Official APEX-I MiniPlus V2.1 canonical release for OpenBMB MiniCPM-V 4.7 35B-A3B, the first Mixture-of-Experts (MoE) multimodal model in the MiniCPM series.

Key Architectural Features:

Canonical 733-Tensor Allocation:
- output.weight protected in Q6_K (1 tensor).
- token_embd.weight protected in Q4_K (1 tensor).
- Normalizations and MoE Expert Routers (ffn_gate_inp) in F32 (zero routing drift).
- Shared foundation experts (shexp) in Q5_K (100% active pathway).
- Periodic full-attention anchors (layers 3, 7, 11, ..., 39) in Q4_K (Q/K/V) and Q6_K (output).
- Recurrent Gated DeltaNet protected states in F32 (ssm_a, ssm_conv1d, ssm_dt, ssm_norm).
- Edge routed experts (layers 0-9 and 30-39) in Q3_K; core routed experts (layers 10-29) in IQ3_XXS.
Multimodal Projector:
- Includes companion mmproj-Q8_0.gguf for high-fidelity visual reasoning without token degradation.

CLI Usage Example:

llama-minicpmv-cli \
  -m MiniCPM-V-4.7-35B-A3B.APEX-I-MiniPlus-V2.1.gguf \
  --mmproj mmproj-Q8_0.gguf \
  --image test.jpg \
  -p "Describe what you see in this image in detail." \
  -c 4096 --temp 0.7