Instructions to use IsValorum/Iris-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/Iris-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/Iris-mini-APEX-I-MiniPlus-V1-GGUF
# Run inference directly in the terminal:
llama cli -hf IsValorum/Iris-mini-APEX-I-MiniPlus-V1-GGUF

Install from WinGet (Windows)

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

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

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

Use Docker

docker model run hf.co/IsValorum/Iris-mini-APEX-I-MiniPlus-V1-GGUF

LM Studio
Jan

vLLM

How to use IsValorum/Iris-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/Iris-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/Iris-mini-APEX-I-MiniPlus-V1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IsValorum/Iris-mini-APEX-I-MiniPlus-V1-GGUF

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

How to use IsValorum/Iris-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/Iris-mini-APEX-I-MiniPlus-V1-GGUF

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/Iris-mini-APEX-I-MiniPlus-V1-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use IsValorum/Iris-mini-APEX-I-MiniPlus-V1-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

lemonade run user.Iris-mini-APEX-I-MiniPlus-V1-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use IsValorum/Iris-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/Iris-mini-APEX-I-MiniPlus-V1-GGUF

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/Iris-mini-APEX-I-MiniPlus-V1-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use IsValorum/Iris-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/Iris-mini-APEX-I-MiniPlus-V1-GGUF

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/Iris-mini-APEX-I-MiniPlus-V1-GGUF" \
  --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"

📜 OPTIMIZATION HISTORY — LEGACY EDITION

This repository hosts a previous iteration of our handcrafted MiniPlus architecture. While not our current specification, it remains an outstanding, high-fidelity quantization that significantly outperforms any flat 3-bit community quants (Q3_K_S / IQ3_S) and generic 2-bit APEX Mini community releases.

We preserve this repository publicly with 100% transparency as a verified engineering record of continuous optimization within the strict 13–14 GB envelope.

👉 Current Definitive Specification (V2.1): Access the newly upgraded V2.1 release featuring zero AVX2 CPU stalls and maximum long-context stability directly at: IsValorum/Iris-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.

MiniPlus V2 (Expanded Edge Defense): Adds wider protective envelopes on edge layers (10 layers in IQ3_S + IQ4_NL shared experts + Q8_0 attention gates) for workstations with an extra ~1 GB of headroom seeking enhanced attention stability.

MiniPlus V2.1 (Current Long-Context Standard): Upgrades shared experts to Q5_K across all 40 layers and optimizes full attention tensors (Q4_K/Q6_K) to eliminate AVX2 CPU dequantization stalls during deep offloading.

💡 Choose the version that fits your exact hardware budget! All editions provide rock-solid reasoning and far exceed generic community quants. 👉 If your workstation has sufficient memory headroom and you want the latest V2.1 specification, you can find it directly at: IsValorum/Iris-mini-APEX-I-MiniPlus-V2.1-GGUF

⚡ Quick Navigation Index

📦 Model Files & Specifications
🔬 Comparative Quantization Analysis (vs. Flat Quants & Generic APEX)
⚡ Native Multi-Token Prediction (MTP) Co-Pilot
💻 Everyday Laptop Benchmarks (23–26+ tok/s on DDR4)
🔥 The 24GB Miracle: Full 256K Context Runs In VRAM!
🏎️ Hardware Throughput Projections (RTX 30 / 40 / 50)
🔬 Why Iris-mini Intentionally Uses Standard APEX (Not V2)
🛠️ Handcrafted Layer Architecture
📖 Recommended Configuration & Setup

📦 Model Files & Specifications

File Name	File Size	Memory Footprint	BPW	Description
`Iris-mini-MTP.APEX-I-MiniPlus.gguf`	`14.84 GB`	`13.82 GiB`	3.42 BPW	Handcrafted language, math, reasoning & native MTP draft head

Base Architecture: qwen35moe (35B total parameters, approx. 3.2B active per token).
Speculative Decoding: Fully preserved native Multi-Token Prediction head (blk.40).
Target Precision: Armored boundaries (Q3_K), calibrated core experts (IQ3_XXS), 6-bit uncompromised output head (Q6_K).

🔬 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 (hitting 23 to 26+ tok/s on DDR4 laptops), while protecting output in Q6_K and routers in F32.

To put the numbers in perspective: this cuts nearly 2 GB off a flat 3-bit quant (approx. 15.6 GB), and weighs only about approx. 1 GB more than a generic APEX-I-Mini (approx. 12.5 GB). For that single extra gigabyte of VRAM, you get a massive jump in reasoning and syntactic stability while maximizing CPU/RAM execution throughput.

Take a look at the tensor-by-tensor comparison table below to inspect the exact architectural differences and see why this specific allocation is optimal. That's specifically what this was built for:

Architectural Component	Generic Automated Quants (Flat `Q3_K_S` / `IQ3_S`)	Generic APEX-I-Mini (Baseline Recipe)	Our Handcrafted APEX-I-MiniPlus (Standard / IsValorum)	Perceived Quality & Real-World Impact
Output Head (`output.weight`)	Flat `IQ3_S` / `Q3_K_S` (approx. 3.44 BPW)	Inherits base type `Q3_K_M` (approx. 3.44 BPW unarmored)	`Q6_K` (approx. 6.56 BPW uncompromised)	Eliminates Syntax & Vocabulary Hallucinations: Low-bit output heads cause tokenizer classification noise, breaking code indentation, brackets (`{}`, `[]`), math symbols, and domain terms. `Q6_K` preserves near-FP16 output classification.
Expert Routers (`ffn_gate_inp.weight`)	Blindly quantized to 3-bit / unoptimized	Inherits base type `Q3_K_M` (approx. 3.44 BPW compressed)	`F32` uncompressed (32.0 BPW, 2 MB/layer)	Zero Router Drift: In micro-expert models, even minuscule quantization errors in router logits misdirect tokens to wrong experts. Retaining uncompressed `F32` guarantees 100% routing fidelity with virtually zero memory overhead (approx. 80 MB total).
Attention & Language (`attn_output`, `attn_qkv`)	Flat `IQ3_S` / `Q3_K_S`	`Q3_K` on 34 middle layers (L3–36), `Q4_K` on 6 edge layers	`Q6_K` for `attn_output`, `Q3_K` / `Q4_K` + `imatrix`	Contextual Precision & CPU Throughput: Combines uncompromised `Q6_K` for the output projection with fast vectorized linear blocks for attention, balancing retrieval accuracy with maximum token streaming speed on CPU/RAM.
Attention Gates (`attn_gate.weight`)	Blindly compressed to 3-bit	Compressed to `Q3_K` (middle) / `Q4_K` (edges)	`Q4_K` / `Q8_0` (linear high-precision)	Attention Routing Dynamics: High-precision linear gating modulating query-key projections without CPU dequantization latency.
*Shared Foundation Expert (`ffn__shexp`)**	Flat `IQ3_S` / `Q3_K_S` (3.44 BPW)	Linear `Q4_K` (middle) / `Q5_K` (edges)	Linear `Q4_K` (middle) / `Q5_K` (edges) + `imatrix`	Foundational Knowledge Stability: Keeps the universal pathway in high-fidelity linear blocks, eliminating quantization drift while maintaining rapid single-cycle dequantization.
Core MoE Layers (Middle: 10–29)	Flat `IQ3_S` / `Q3_K_S` (uniform bit-rate across all layers)	Aggressive `IQ2_S` (2.50 BPW)	`IQ3_XXS` (3.06 BPW) + calibrated `imatrix`	Above the Quality Threshold: Generic 2-bit `IQ2_S` baselines drop below the critical quality floor for 35B MoEs, resulting in perplexity spikes on reasoning tasks. Our `IQ3_XXS` with imatrix achieves deep compression (272 MiB → 98 MiB per block) without sacrificing logic.
Edge MoE Layers (Layers 0–9 & 30–39)	Flat `IQ3_S` / `Q3_K_S` (no layer-wise gradient)	`Q3_K` (limited to first/last 5 layers only: L0–4, L35–39)	`Q3_K` (expanded to 10 input & 10 output layers)	AVX2 Single-Cycle Speed: Expanded 10+10 layer protection using linear `Q3_K` blocks enables single-cycle vectorized AVX2 CPU dequantization, unlocking 23 to 26+ tok/s on budget DDR4 laptops.
MTP Draft Block (`blk.40`)	Stripped with `--no-mtp` or broken	Crushed to `IQ2_S` / tier precision	Preserved in `IQ3_S` / `Q3_K` & `IQ4_NL`	Speculative Decoding Speedup: Maintains 58%–65% candidate acceptance rate, yielding 1.6x–1.75x real-world token speedup without speculative rejection waste.
Normalization & Biases	Often degraded	Standard	`F32` uncompressed	Numerical Stability: Prevents cumulative floating-point underflow/overflow across deep 40-layer computation.

⚡ Native Multi-Token Prediction (MTP) Co-Pilot

Most automated community releases strip or break the native Multi-Token Prediction head using --no-mtp. APEX-I-MiniPlus fully preserves and calibrates the native prediction block (blk.40):

Zero-Cost Speculative Acceleration: Unlike external draft models that consume separate VRAM and memory bandwidth, Iris-mini's native MTP head is integrated directly into the weights.
Empirical Acceptance Rate: 58.8% to 65.5% of predicted candidate tokens are accepted on full GPU offload.
Token Yield: Delivers 1.60 to 1.75 tokens per forward step on standard text, peaking at 2.0+ tokens/step during continuous code and prose generation.
Net Speedup: Provides approx. 1.6x faster real-world generation without quality degradation.

💻 Everyday Laptop Benchmarks (23–26+ tok/s on DDR4)

VRAM Allocation: 3.8 GB VRAM utilized on budget 4GB/6GB GPUs.
System Memory: 32GB DDR4 holds the remaining layers.
Prefill Speed: 300 to 410 tokens/second sustained across dense inputs.
Generation Speed: 23 to 26+ tokens/second sustained on standard DDR4 RAM!

🔥 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 Feasibility
32,512 (32k)	`13.82 GiB`	`0.58 GiB`	`1.80 GiB`	`16.20 GiB`	Full offload on 24GB; partial on 16GB
64,512 (64k)	`13.82 GiB`	`0.92 GiB`	`1.95 GiB`	`16.69 GiB`	Effortless fit on 24GB GPUs
128,640 (128k)	`13.82 GiB`	`1.58 GiB`	`2.22 GiB`	`17.62 GiB`	Effortless fit on 24GB GPUs
262,144 (Full 256K)	`13.82 GiB`	`2.92 GiB`	`2.80 GiB`	`19.54 GiB`	🔥 FULL 256K NATIVE IN VRAM!

🏎️ Hardware Throughput Projections (RTX 30 / 40 / 50)

🔬 Why Iris-mini Intentionally Uses Standard APEX (Not V2)

Unlike Occamy and Apodex which use non-linear IQ codebooks, Iris-mini intentionally uses linear AVX2-vectorized Q_K blocks on boundaries:

Linear Q3_K and Q4_K execute in single-cycle AVX2 instructions without table lookup overhead on CPUs.
This allows Iris-mini to achieve 23–26+ tok/s on everyday DDR4 laptops, making it the fastest 35B speculative assistant available.

🛠️ Handcrafted Layer Architecture

Component	Target Layers	Quant Type	Rationale
Output Head (`output.weight`)	Final projection	`Q6_K`	Preserves probability distributions across 248k vocabulary tokens
Token Embeddings	Input projection	`Q3_K`	High semantic input fidelity
Expert Routers (`ffn_gate_inp`)	All layers (0–39)	`F32`	Uncompressed 32-bit floating point; 100% exact expert selection without routing noise
Attention Output (`attn_output`)	All layers	`Q6_K`	Uncompromised 6-bit attention projection across all layers
Attention QKV & SSM States	All layers	`Q3_K / Q4_K`	Fast vectorized AVX2 linear dequantization for tool-use responsiveness
Core Routed Experts	Layers 10 to 29	`IQ3_XXS`	Maximum parameter compression (3.06 bpw) with importance matrix guidance
Core Shared Experts	Layers 10 to 29	`Q4_K`	High-precision shared expert routing
Edge Routed Experts	Layers 0 to 9 & 30 to 39	`Q3_K`	Protects prompt ingestion and response synthesis boundaries
Edge Shared Experts	Layers 0 to 9 & 30 to 39	`Q4_K`	Armors foundational reasoning
MTP Draft Block (`blk.40`)	Speculative Head	`Q3_K / Q4_K`	High candidate acceptance rate
Normalization & Biases	All layers	`F32`	Prevents cumulative floating point error

📖 Recommended Configuration & Setup

Unsloth Studio:

Load Iris-mini-MTP.APEX-I-MiniPlus.gguf.
Set Speculative Decoding to draft-mtp or set Draft Tokens to 1.
Configure KV Cache Dtype to q8_0 and Context Checkpoints to 1.

llama.cpp CLI:

llama-cli -m Iris-mini-MTP.APEX-I-MiniPlus.gguf \
  --spec-type draft-mtp \
  -ngl 99 \
  -c 32768

Downloads last month: 845

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for IsValorum/Iris-mini-APEX-I-MiniPlus-V1-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

AllSpark-Research/Iris-mini

Quantized

(4)

this model

Collections including IsValorum/Iris-mini-APEX-I-MiniPlus-V1-GGUF

APEX-I Custom Quants

Collection

Handcrafted APEX-I GGUFs optimized for 4GB-24GB VRAM setups with high throughput. • 7 items • Updated about 21 hours ago

Olds MiniPlus V1

Collection

Historical legacy collection of early APEX-I-MiniPlus V1 quantization releases. • 2 items • Updated about 10 hours ago