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 16 days ago

Commit

1cd0a4d

verified ·

1 Parent(s): dd6ecfc

Update tailored Architecture Selection Guide

Browse files

Files changed (1) hide show

README.md +9 -11

README.md CHANGED Viewed

@@ -35,20 +35,18 @@ quantized_by: IsValorum
 ---
 > [!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

 ---
 > [!NOTE]
+> ### 🏛️ ARCHITECTURE SELECTION GUIDE — MINIPLUS V1 & V2.1 EDITIONS
+> This repository hosts the **MiniPlus V1** edition of **Nex-N2.5-mini**. Our releases are precision-engineered for specific hardware budgets and memory topologies. **V1 is NOT obsolete or inferior; it represents our leanest, most agile operating profile:**
 >
+> - **MiniPlus V1 (Lean & Agile Profile):** Highly compact footprint with uncompressed `F32` router gates, a fully armored `Q6_K` output head, and `IQ3_XXS` core experts. **Both V1 and V2.1 run flawlessly with the vast majority of the model residing in system RAM (DDR4/DDR5)**, thanks to linear CPU-friendly vectorization that avoids lookup stalls. V1 is dramatically superior to generic community APEX-I-Mini releases (which crush core reasoning down to 2-bit `IQ2_S`) and flat 3-bit quants.
+> - **MiniPlus V2.1 (Enhanced Protection & Refined Throughput):** Upgrades all 40 shared foundation experts to high-precision `Q5_K` and armors full attention anchor layers (`Q4_K`/`Q6_K`). This improves inference speed and stability even further for **only a few hundred megabytes extra** (~13.74 GiB vs ~13.56 GiB)—an overhead that is completely negligible when running in system RAM (16GB/32GB/64GB).
 >
+> 💡 **Which one should you choose?**
+> - **If your system has strict memory constraints:** **V1** delivers uncompromising reasoning at our lowest RAM footprint.
+> - **If you have a few hundred MBs of headroom in RAM:** **V2.1** provides our latest long-context protection and enhanced throughput.
+> - **If you have 24GB+ VRAM (`-ngl 99`):** Both **V1 and V2.1** run blistering fast with virtually identical top-tier quality.
 >
+> 👉 To explore or download the **V2.1** edition of Nex-N2.5-mini, 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