IsValorum/Apodex-1.1-mini-APEX-I-MiniPlus-V2-GGUF

[!NOTE]

ARCHITECTURE SELECTION GUIDE — MINIPLUS V2 & V2.1 EDITIONS

This repository hosts the MiniPlus V2 edition of Apodex-1.1-mini. Our releases are precision-engineered for specific hardware budgets and memory topologies. V2 is NOT obsolete or "worse"; each edition serves distinct inference requirements:

MiniPlus V2 (High Theoretical Layer Protection): On paper, V2 provides extra protective envelopes on edge layers (10 layers in IQ3_S + IQ4_NL shared experts + Q8_0 attention gates). However, in practical inference benchmarks—even across extreme long-context windows exceeding +160K tokens—there is virtually NO perceptible difference in quality or reasoning compared to V2.1.

MiniPlus V2.1 (System RAM Streaming Specialist with Deep Context): Specially prepared to run totally or partially in system RAM (DDR4/DDR5) across deep biomedical literature and scientific papers (up to 256k tokens). By replacing non-linear codebooks with linear Q3_K edge experts, keeping Q8_0 attention gates, and upgrading shared foundation experts to Q5_K across all 40 layers, it completely eliminates AVX2 CPU dequantization stalls (+24 to 28+ tok/s streaming). Depending on your processor and memory bandwidth (DDR4/DDR5), streaming generation in system RAM can be almost as fast as having everything in VRAM, while supporting deep context keeping the dedicated Q8_0 multimodal vision projector (mmproj) explicitly loaded in GPU VRAM for scientific figures and molecular diagram reading. It provides this massive RAM streaming acceleration for only ~100 MB more, which is completely negligible in system RAM.

Which one should you choose? (Official Recommendation: V2.1)

⭐ PRIMARY RECOMMENDATION — Apodex-1.1-mini APEX-I-MiniPlus V2.1: For virtually all users and deployments, V2.1 is the strictly recommended release. Empirically verified on WikiText-2, V2.1 achieves an outstanding Perplexity of 5.7073 ± 0.1373 (empirically verified on WikiText-2 with near-lossless precision matching Q5_K/Q6_K quality), matching the token fidelity of Q5_K / Q6_K class quantizations while weighing only ~14.7 GB (same footprint as Q3_K_M). Furthermore, it completely eliminates AVX2 CPU stalls, providing blistering +24 to 28+ tok/s streaming under system RAM offload.

MiniPlus V2 Legacy: Maintained for architectural transparency and users seeking specialized configurations for their workflow.

Both editions are handcrafted and vastly outperform flat 3-bit quants and generic community APEX-I-Mini releases. To explore or download the V2.1 edition of Apodex-1.1-mini optimized for system RAM streaming, visit: IsValorum/Apodex-1.1-mini-APEX-I-MiniPlus-V2.1-GGUF

[!WARNING]

DO NOT CONFUSE APEX-I-MINIPLUS WITH GENERIC COMMUNITY APEX-I-MINI!

Regardless of release version (whether V1, V2, or V2.1), NEVER confuse handcrafted APEX-I-MiniPlus builds with generic community APEX-I-Mini releases:

Generic Community APEX-I-Mini: Uniformly compresses all core MoE experts down to aggressive 2-bit IQ2_S (dropping below the critical quality floor), leaves the sensitive token output head unarmored at 3-bit Q3_K_M, and compresses attention projections down to Q3_K. In deep reasoning models, this triggers severe perplexity spikes, syntax errors, and broken code brackets.

Handcrafted APEX-I-MiniPlus (All Editions by IsValorum): Every single MiniPlus release—from V1 and V2 to V2.1—is a custom tensor-by-tensor architecture that preserves uncompressed F32 router gates, armors the token output head in high-precision Q6_K, safeguards attention gates in Q8_0, and keeps core reasoning experts at or above calibrated 3-bit (IQ3_XXS/IQ3_S). Even our earlier builds vastly outperform generic community APEX recipes and flat 3-bit quants.

Quick Navigation Index

Model Files & Specifications
Comparative Quantization Analysis (vs. Flat Quants & Generic APEX)
Native Multi-Token Prediction (MTP) Acceleration
Bundled Q8_0 High-Precision Vision Projector
Everyday Laptop Benchmarks (DDR4 / DDR5 RAM)
The 24GB Miracle: Full 256K Context Runs In VRAM!
Hardware Throughput Projections (RTX 30 / 40 / 50)
Surgical Tensor Quantization Map
Recommended Configuration & Setup

Model Files & Specifications

File Name	File Size	Memory Footprint	BPW	Description
`Apodex-1.1-mini-MTP.APEX-I-MiniPlus-V2.gguf`	`14.65 GB` (`13.65 GiB`)	`13.65 GiB`	3.38 BPW	Core language, vision, reasoning & native MTP draft block
`mmproj-apodex_Apodex-1.1-mini-Q8_0.gguf`	`610 MB` (`582 MiB`)	`582 MiB`	8.50 BPW	Dedicated `Q8_0` vision projector for optical document parsing

Base Architecture: Qwen3_5MoeForConditionalGeneration (40 layers + layer 40 native MTP block, 256 micro-experts).
Active Parameters: approx. 3.2B active parameters per token.

Comparative Quantization Analysis (vs. Flat Quants & Generic APEX)

Also, don't confuse APEX-I-MiniPlus-V2 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. V2 was specifically re-engineered to avoid that quality floor (keeping core experts at calibrated IQ3_XXS, output in Q6_K, shared expert in non-linear IQ4_NL, 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.

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-V2 (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`, `IQ3_S` for `attn_qkv`	Contextual Retrieval Precision: Generic APEX reduces attention and language projections to `Q3_K` across 85% of layers. Our V2 build protects attention output in high-precision `Q6_K` and uses calibrated non-linear `IQ3_S`, ensuring flawless needle-in-a-haystack retrieval across deep 128k–256k context windows.
Attention Gates (`attn_gate.weight`)	Blindly compressed to 3-bit	Compressed to `Q3_K` (middle) / `Q4_K` (edges)	`Q8_0` (8.50 BPW)	Attention Head Stability: Attention gates modulate query-key routing across hybrid attention layers. Keeping them in 8-bit prevents attention crosstalk and hallucination over long contexts.
*Shared Foundation Expert (`ffn__shexp`)**	Flat `IQ3_S` / `Q3_K_S` (3.44 BPW)	Linear `Q4_K` (middle) / `Q5_K` (edges)	`IQ4_NL` (4.50 BPW non-linear codebook)	Foundational Knowledge Armor: The shared expert executes for 100% of tokens. In 256 micro-expert models, `IQ4_NL` non-linear codebooks preserve heavy-tailed outlier representations far better than standard linear quantization.
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)	`IQ3_S` (expanded to 10 input & 10 output layers)	Protected Ingestion & Synthesis: Half of the model's layers (10 at input, 10 at output) form a non-linear armored envelope, preventing prompt misunderstanding and token degeneration across 256 micro-experts.
Multimodal Vision (`mmproj`)	Often omitted, or left as uncompressed `FP16` (approx. 900 MB)	Often omitted or separate uncompressed `FP16`	Bundled `Q8_0` (582 MB) with 27 critical F32/F16 fallbacks	Saves approx. 320 MB VRAM with Zero Loss: Handcrafted quantization preserves normalization and bias tensors in F32/F16, ensuring razor-sharp OCR, DOM viewport reading, and coordinate detection without visual noise.
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) Acceleration

Integrated Speculative Decoding: Unlike external draft models that consume separate VRAM, Apodex's native MTP head (blk.40) is integrated directly into the weights.
High Acceptance Rate: Achieves 58% to 65% draft candidate acceptance on full GPU offload.
Real Speedup: Yields 1.60x to 1.75x real-world token speedup on continuous text and code.

Bundled Q8_0 High-Precision Vision Projector

Bundled Q8_0 Projector: Pre-quantized to Q8_0 (582 MiB / 610 MB), saving approx. 300 MB of VRAM.
Audited Layer Fallbacks: llama.cpp automatically preserved 27 critical normalization and embedding tensors in F32/F16, ensuring razor-sharp OCR without artifacts.

Everyday Laptop Benchmarks (DDR4 / DDR5 RAM)

Estimated Projections on Consumer Hardware

GPU VRAM Allocation: Uses only approx. 3.8 GB VRAM.
System Memory Offload: Standard 32GB system RAM accommodates the remaining layers.
Estimated Document Ingestion (Prefill): 300 to 420+ tokens/second.
Estimated Streaming Generation: 20 to 24+ tokens/second sustained output.

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
32,768 (32k)	`13.65 GiB`	`0.58 GiB`	`1.80 GiB`	`16.03 GiB`	Full offload on 24GB; partial on 16GB
65,536 (64k)	`13.65 GiB`	`0.92 GiB`	`1.95 GiB`	`16.52 GiB`	Effortless fit on 24GB GPUs
131,072 (128k)	`13.65 GiB`	`1.58 GiB`	`2.22 GiB`	`17.45 GiB`	Effortless fit on 24GB GPUs
262,144 (256k)	`13.65 GiB`	`2.92 GiB`	`2.80 GiB`	`19.37 GiB`	FULL 256K IN VRAM!

Hardware Throughput Projections (RTX 30 / 40 / 50)