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 3 days ago

Commit

d3fb3ca

verified ·

1 Parent(s): 0456a4c

Complete navigation index and remove duplicate support block

Browse files

Files changed (1) hide show

README.md +20 -11

README.md CHANGED Viewed

@@ -34,18 +34,17 @@ pipeline_tag: image-text-to-text
 quantized_by: IsValorum
 ---
 ## <a id="quick-navigation"></a>Quick Navigation Index
-- [Model Files & Technical Specifications](#model-specifications)
-- [Comparative Quantization Analysis (vs. Flat Quants & Generic APEX)](#comparative-analysis)
-- [Independent Benchmark of the APEX-I-MiniPlus Family (Occamy V2 Reference)](#independent-benchmark)
-- [Bundled Q8_0 High-Precision Vision Projector](#vision-projector)
-- [Everyday Laptop Guidance (DDR4 / DDR5 RAM)](#laptop-benchmarks)
-- [The 24GB Miracle: Full 256K Context Runs In VRAM!](#context-scaling)
-- [Hardware Throughput & Offload Benchmarks (RTX 30 / 40 / 50)](#throughput-projections)
-- [Recommended Generation Parameters (Creator Official)](#generation-parameters)
-- [Model Inherent Behavior vs. Quantization Fidelity Notice](#quantization-fidelity)
-- [Optional Support](#optional-support)
 > [!NOTE]
 > ### ARCHITECTURE SELECTION GUIDE — MINIPLUS V1 & V2.1 EDITIONS
@@ -92,6 +91,7 @@ quantized_by: IsValorum
 ---
 <a id="independent-benchmark"></a>
 ### 🏅 Independent Benchmark of the APEX-I-MiniPlus Family (Occamy V2 Reference)
@@ -115,6 +115,7 @@ The evaluation tested the APEX-I hybrid MoE engine across **348 unseeded trials*
 ---
 <a id="model-specifications"></a>
 ## Model Files & Specifications
 | File Name | File Size | Memory Footprint | BPW | Description |
@@ -128,6 +129,7 @@ The evaluation tested the APEX-I hybrid MoE engine across **348 unseeded trials*
 ---
 <a id="comparative-analysis"></a>
 ## Comparative Quantization Analysis (vs. Flat Quants & Generic APEX)
 Also, don't confuse **APEX-I-MiniPlus (Standard)** with a generic baseline APEX-I-Mini. Traditional APEX-I-Mini drops core experts aggressively to 2-bit `IQ2_S` and leaves `output.weight` at 3-bit `Q3_K_M`, which creates a noticeable perplexity hit on complex reasoning tasks. Standard MiniPlus avoids that degradation floor while keeping boundary layers in linear `Q3_K` for single-cycle vectorized AVX2 CPU dequantization (optimized for DDR4/DDR5 laptop streaming), while protecting output in `Q6_K` and routers in `F32`.
@@ -151,6 +153,7 @@ Take a look at the tensor-by-tensor comparison table below to inspect the exact
 ---
 <a id="vision-projector"></a>
 ## Bundled Q8_0 High-Precision Vision Projector
 Unlike text-only MoEs, Nex-N2.5-mini is designed for computer use, visual grounding, and multi-modal interaction.
@@ -160,7 +163,9 @@ Unlike text-only MoEs, Nex-N2.5-mini is designed for computer use, visual ground
 ---
 <a id="laptop-benchmarks"></a>
 ## Everyday Laptop Guidance
 ### *Empirically Verified in Unsloth Studio*
 - **GPU VRAM Offload:** Uses only **3.8 GB VRAM** (fits effortlessly on budget 4GB and 6GB laptop GPUs like the RTX 4050, 3050, or older 1660 Ti/2060).
@@ -171,6 +176,7 @@ Unlike text-only MoEs, Nex-N2.5-mini is designed for computer use, visual ground
 ---
 <a id="context-scaling"></a>
 ## The 24GB Miracle: Full 256K Context Runs In VRAM!
 | Context Length | Model Weights (Est.) | KV Cache (q8_0, 4 slots) | Compute Buffers | **Total GPU VRAM (Est.)** | Hardware Verdict |
@@ -183,6 +189,7 @@ Unlike text-only MoEs, Nex-N2.5-mini is designed for computer use, visual ground
 ---
 <a id="throughput-projections"></a>
 ## Hardware Throughput Projections (RTX 30 / 40 / 50)
 | Hardware Target | Offload Mode | Generation Speed (Est.) | Prompt Prefill Speed (Est.) | Highlights |
@@ -193,6 +200,7 @@ Unlike text-only MoEs, Nex-N2.5-mini is designed for computer use, visual ground
 | **Consumer Laptop (4GB GPU + 32GB RAM)**| Hybrid Offload | Hardware-dependent | Hardware-dependent | Smooth streaming from system DDR4/DDR5 RAM |
 <a id="generation-parameters"></a>
 ### ⚙️ Recommended Generation Parameters (nex-agi Official)
 Official sampling configuration recommended by [nex-agi](https://huggingface.co/nex-agi/Nex-N2.5-mini) for optimal generation quality across coding, browser-use, and agent evaluations:
@@ -210,6 +218,7 @@ Official sampling configuration recommended by [nex-agi](https://huggingface.co/
 > Any behavioral nuances, stylistic tendencies, domain-specific habits, or zero-shot edge-case oversights **stem entirely from the original unquantized checkpoint weights and fine-tuning distribution, NOT from the APEX-I quantization process.**
 > Handcrafted APEX-I-MiniPlus strictly preserves mathematical tensor fidelity—keeping 100% of expert routing matrices (`gate_inp`) in uncompressed `F32` (zero router drift), armoring the token output head in `Q6_K`, and safeguarding attention gates in `Q8_0`. Empirical verification confirms near-zero perplexity loss (ΔPPL ≈ +0.07), ensuring that token logits, routing decisions, and reasoning trajectories are mathematically faithful to the original base model.
 ## Optional Support
 > [!NOTE]

 quantized_by: IsValorum
 ---
 ## <a id="quick-navigation"></a>Quick Navigation Index
+- [🏅 Independent Benchmark of the APEX-I-MiniPlus Family (Occamy V2 Reference)](#toc-01)
+- [Model Files & Specifications](#toc-02)
+- [Comparative Quantization Analysis (vs. Flat Quants & Generic APEX)](#toc-03)
+- [Bundled Q8_0 High-Precision Vision Projector](#toc-04)
+- [Everyday Laptop Guidance](#toc-05)
+- [Empirically Verified in Unsloth Studio](#toc-06)
+- [The 24GB Miracle: Full 256K Context Runs In VRAM!](#toc-07)
+- [Hardware Throughput Projections (RTX 30 / 40 / 50)](#toc-08)
+- [⚙️ Recommended Generation Parameters (nex-agi Official)](#toc-09)
+- [Optional Support](#toc-10)
 > [!NOTE]
 > ### ARCHITECTURE SELECTION GUIDE — MINIPLUS V1 & V2.1 EDITIONS
 ---
 <a id="independent-benchmark"></a>
+<a id="toc-01"></a>
 ### 🏅 Independent Benchmark of the APEX-I-MiniPlus Family (Occamy V2 Reference)
 ---
 <a id="model-specifications"></a>
+<a id="toc-02"></a>
 ## Model Files & Specifications
 | File Name | File Size | Memory Footprint | BPW | Description |
 ---
 <a id="comparative-analysis"></a>
+<a id="toc-03"></a>
 ## Comparative Quantization Analysis (vs. Flat Quants & Generic APEX)
 Also, don't confuse **APEX-I-MiniPlus (Standard)** with a generic baseline APEX-I-Mini. Traditional APEX-I-Mini drops core experts aggressively to 2-bit `IQ2_S` and leaves `output.weight` at 3-bit `Q3_K_M`, which creates a noticeable perplexity hit on complex reasoning tasks. Standard MiniPlus avoids that degradation floor while keeping boundary layers in linear `Q3_K` for single-cycle vectorized AVX2 CPU dequantization (optimized for DDR4/DDR5 laptop streaming), while protecting output in `Q6_K` and routers in `F32`.
 ---
 <a id="vision-projector"></a>
+<a id="toc-04"></a>
 ## Bundled Q8_0 High-Precision Vision Projector
 Unlike text-only MoEs, Nex-N2.5-mini is designed for computer use, visual grounding, and multi-modal interaction.
 ---
 <a id="laptop-benchmarks"></a>
+<a id="toc-05"></a>
 ## Everyday Laptop Guidance
+<a id="toc-06"></a>
 ### *Empirically Verified in Unsloth Studio*
 - **GPU VRAM Offload:** Uses only **3.8 GB VRAM** (fits effortlessly on budget 4GB and 6GB laptop GPUs like the RTX 4050, 3050, or older 1660 Ti/2060).
 ---
 <a id="context-scaling"></a>
+<a id="toc-07"></a>
 ## The 24GB Miracle: Full 256K Context Runs In VRAM!
 | Context Length | Model Weights (Est.) | KV Cache (q8_0, 4 slots) | Compute Buffers | **Total GPU VRAM (Est.)** | Hardware Verdict |
 ---
 <a id="throughput-projections"></a>
+<a id="toc-08"></a>
 ## Hardware Throughput Projections (RTX 30 / 40 / 50)
 | Hardware Target | Offload Mode | Generation Speed (Est.) | Prompt Prefill Speed (Est.) | Highlights |
 | **Consumer Laptop (4GB GPU + 32GB RAM)**| Hybrid Offload | Hardware-dependent | Hardware-dependent | Smooth streaming from system DDR4/DDR5 RAM |
 <a id="generation-parameters"></a>
+<a id="toc-09"></a>
 ### ⚙️ Recommended Generation Parameters (nex-agi Official)
 Official sampling configuration recommended by [nex-agi](https://huggingface.co/nex-agi/Nex-N2.5-mini) for optimal generation quality across coding, browser-use, and agent evaluations:
 > Any behavioral nuances, stylistic tendencies, domain-specific habits, or zero-shot edge-case oversights **stem entirely from the original unquantized checkpoint weights and fine-tuning distribution, NOT from the APEX-I quantization process.**
 > Handcrafted APEX-I-MiniPlus strictly preserves mathematical tensor fidelity—keeping 100% of expert routing matrices (`gate_inp`) in uncompressed `F32` (zero router drift), armoring the token output head in `Q6_K`, and safeguarding attention gates in `Q8_0`. Empirical verification confirms near-zero perplexity loss (ΔPPL ≈ +0.07), ensuring that token logits, routing decisions, and reasoning trajectories are mathematically faithful to the original base model.
+<a id="toc-10"></a>
 ## Optional Support
 > [!NOTE]