Instructions to use IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

Use Docker

docker model run hf.co/IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

Ollama
How to use IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF with Ollama:
```
ollama run hf.co/IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0
```
Unsloth Desktop

How to use IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF with Docker Model Runner:
```
docker model run hf.co/IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0
```

Lemonade

How to use IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

Run and chat with the model

lemonade run user.Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V1-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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0

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/Nex-N2.5-mini-APEX-I-MiniPlus-V1-GGUF:Q8_0" \
  --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"

IsValorum commited on 14 days ago

Commit

dd6ecfc

verified ·

1 Parent(s): f3eb1b8

Update Architecture Selection Guide: transparent comparison of V1, V2, and V2.1

Browse files

Files changed (1) hide show

README.md +17 -1

README.md CHANGED Viewed

@@ -35,7 +35,23 @@ quantized_by: IsValorum
 ---
 > [!NOTE]
-> ### 🏛️ ARCHITECTURE SELECTION GUIDE — MINIPLUS TIER OVERVIEW
 > Every edition of the **MiniPlus** family is a precision-engineered, handcrafted quantization designed for specific hardware constraints and memory footprints. **None of these releases are obsolete; each represents an optimal operating point tailored to your system budget:**
 >
 > - **MiniPlus V1 (Lean & Agile Foundation):** Maximum compactness and ultra-fast throughput with minimal RAM/VRAM footprint. Even in this lightest profile, **V1 dramatically outperforms generic community APEX-I-Mini releases** (which aggressively downgrade core reasoning to flat 2-bit `IQ2_S` and leave attention and output heads degraded). V1 provides uncompressed `F32` router gates, `Q6_K` output head protection, and `IQ3_XXS` core experts.

 ---
 > [!NOTE]
+> ### 🏛️ ARCHITECTURE SELECTION GUIDE — MINIPLUS FAMILY OVERVIEW
+> Every edition of the **MiniPlus** family (engineered by **IsValorum**) is a precision-crafted, surgical quantization designed for specific hardware topologies and inference budgets. **None of these releases are obsolete or "inferior"; each represents an optimal operating profile tailored to your specific hardware setup:**
+>
+> - **MiniPlus V1 (Lightweight & Agile Profile):** The most compact footprint. Preserves uncompressed `F32` router gates, a fully armored `Q6_K` token output head, and `IQ3_XXS` core experts. **Even in this leanest profile, V1 is vastly superior to generic community APEX-I-Mini releases** (which aggressively degrade core reasoning to 2-bit `IQ2_S` and leave attention and output heads degraded). Best for systems with tightest RAM/VRAM constraints.
+> - **MiniPlus V2 (High Theoretical Layer Protection):** Widens protective envelopes on edge layers (10 layers in `IQ3_S` + `IQ4_NL` shared experts). While V2 technically provides higher protection on paper, **in practical inference benchmarks there is virtually no noticeable quality difference compared to V1**. If you offload the entire model to **GPU VRAM (`-ngl 99`)**, V2 runs blazing fast with full hardware acceleration.
+> - **MiniPlus V2.1 (System RAM Streaming Specialist):** Specifically engineered for hybrid and CPU RAM inference. Replaces non-linear edge experts with linear `Q3_K` and upgrades shared foundation experts to `Q5_K` across all 40 layers. This completely eliminates AVX2 CPU dequantization stalls, delivering **+24 to 28+ tok/s streaming even when running almost the entire model in system RAM (DDR4/DDR5)**. The overhead is only **~90 to 100 MB over V2**, which is completely negligible when running in system RAM.
+>
+> 💡 **Summary Guide:**
+> - **If your model fits entirely into GPU VRAM (24GB+):** Any version (**V1, V2, or V2.1**) will deliver virtually identical, top-tier quality and blistering throughput.
+> - **If you are offloading primarily to system RAM (DDR4/DDR5):** **V2.1** is strongly recommended for its zero-stall AVX2 linear execution (+24 to 28+ tok/s).
+> - **If you need the smallest possible memory footprint:** **V1** gives you uncompromising MoE reasoning in the leanest package.
+>
+> *All MiniPlus editions are handcrafted and dramatically outperform flat 3-bit quants and generic community baselines.*
+> 👉 If your workstation has memory headroom and you want the latest V2.1 specification optimized for system RAM streaming, visit:
+> **[IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF](https://huggingface.co/IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF)**
+# 🏛️ ARCHITECTURE SELECTION GUIDE — MINIPLUS TIER OVERVIEW
 > Every edition of the **MiniPlus** family is a precision-engineered, handcrafted quantization designed for specific hardware constraints and memory footprints. **None of these releases are obsolete; each represents an optimal operating point tailored to your system budget:**
 >
 > - **MiniPlus V1 (Lean & Agile Foundation):** Maximum compactness and ultra-fast throughput with minimal RAM/VRAM footprint. Even in this lightest profile, **V1 dramatically outperforms generic community APEX-I-Mini releases** (which aggressively downgrade core reasoning to flat 2-bit `IQ2_S` and leave attention and output heads degraded). V1 provides uncompressed `F32` router gates, `Q6_K` output head protection, and `IQ3_XXS` core experts.