| --- |
| base_model: nex-agi/Nex-N2.5-mini |
| library_name: gguf |
| tags: |
| - quantization |
| - quantized |
| - gguf |
| - apex |
| - custom-quantization |
| - unsloth-studio |
| - moe |
| - multimodal |
| - vision |
| - agentic |
| - computer-use |
| - llama.cpp |
| - qwen35moe |
| license: apache-2.0 |
| language: |
| - en |
| - zh |
| - es |
| - fr |
| - de |
| - pt |
| - it |
| - ru |
| - ja |
| - ko |
| - vi |
| - th |
| - ar |
| pipeline_tag: image-text-to-text |
| quantized_by: IsValorum |
| --- |
| |
| ## <a id="quick-navigation"></a>Quick Navigation Index |
| 1. [Independent Benchmark of the APEX-I-MiniPlus Family (Occamy V2 Reference)](#toc-01) |
| 2. [Model Files & Specifications](#toc-02) |
| 3. [Comparative Quantization Analysis (vs. Flat Quants & Generic APEX)](#toc-03) |
| 4. [Bundled Q8_0 High-Precision Vision Projector](#toc-04) |
| 5. [Everyday Laptop Guidance](#toc-05) |
| 6. [Empirically Verified in Unsloth Studio](#toc-06) |
| 7. [The 24GB Miracle: Full 256K Context Runs In VRAM!](#toc-07) |
| 8. [Hardware Throughput Projections (RTX 30 / 40 / 50)](#toc-08) |
| 9. [Recommended Generation Parameters (nex-agi Official)](#toc-09) |
| 10. [Optional Support](#toc-10) |
|
|
| > [!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, `Q8_0` attention gates, 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 (System RAM Streaming Specialist with Deep Context):** Specially prepared to run **totally or partially in system RAM (DDR4/DDR5)** across massive multimodal and agentic context windows (up to 256k tokens). Upgrades all 40 shared foundation experts to `Q5_K`, armors attention gates in `Q8_0`, and uses linear CPU-friendly vectorization that eliminates AVX2 lookup stalls. 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 instant screen parsing and OCR. All for **only approx. 180 MB more** (approx. 13.74 GiB vs approx. 13.56 GiB)—an overhead that is completely negligible in system RAM. |
| > |
| > **Which one should you choose? (Official Recommendation: V2.1)** |
| > - **⭐ PRIMARY RECOMMENDATION — [Nex-N2.5-mini APEX-I-MiniPlus V2.1](https://huggingface.co/IsValorum/Nex-N2.5-mini-APEX-I-MiniPlus-V2.1-GGUF):** For virtually all users and deployments, **V2.1 is the strictly recommended release**. V2.1 reports a **Perplexity of 6.4725 ± 0.1635** (ΔPPL ≈ +0.07 from unquantized baseline (approx. 6.40)), matching the token fidelity of **Q5_K / Q6_K** class quantizations while weighing only **approx. 14.7 GB** (same footprint as Q3_K_M). Furthermore, it eliminates AVX2 CPU stalls and is optimized for system RAM offload. |
| > - **MiniPlus V1 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 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)** |
| |
| > [!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. |
| |
| |
| > [!TIP] |
| > ### SYSTEM RAM INFERENCE: FULL OR PARTIAL |
| > This APEX-I-MiniPlus release is designed for **full or partial system-RAM inference**. Depending on the processor, memory bandwidth, and DDR4/DDR5 configuration, generation can range from **20 to 45 tok/s**. With partial GPU offload, systems that cannot fit **128K or more context** entirely in VRAM can place the remaining model and context load in system RAM, maintaining stable, responsive generation at longer context lengths. |
| |
| --- |
| |
| > [!IMPORTANT] |
| > ### EXPLORE THE ESTABLISHED 35B MoE MINIPLUS LINEUP |
| > These are complementary APEX-I-MiniPlus V2.1 releases, not alternate downloads of the same model. Each receives the same tensor-by-tensor approach, integrated MTP where supported, and a design suitable for full or partial system-RAM inference. Choose the model whose native strengths best fit the work you want to do: |
| > |
| > - **[Qwen3.6-35B-A3B MTP APEX-I-MiniPlus-V2.1](https://huggingface.co/IsValorum/Qwen3.6-35B-A3B-MTP-APEX-I-MiniPlus-V2.1-GGUF)** — a versatile frontier MoE for broad reasoning, multilingual work, agents, tool use, and multimodal tasks. |
| > - **Best for:** General reasoning, agent workflows, tool calling, and flexible multimodal use. |
| > - **[Qwen3.6-35B-A3B MTP APEX-I-MiniPlus-V2.1 Abliterated](https://huggingface.co/IsValorum/Qwen3.6-35B-A3B-MTP-APEX-I-MiniPlus-V2.1-Abliterated-GGUF)** — the V2.1 refusal-ablated Qwen3.6 edition for users who deliberately prefer reduced refusal behavior. |
| > - **Best for:** Workflows where an abliterated Qwen3.6 variant is explicitly desired. |
| > - **[Ornith 1.5 APEX-I-MiniPlus-V2.1](https://huggingface.co/IsValorum/Ornith-1.5-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF)** — a software-engineering-focused MoE designed for repository-scale coding and autonomous engineering agents. |
| > - **Best for:** Repository-scale development, multi-file code changes, and software-engineering agents. |
| > - **[Tiel Coder APEX-I-MiniPlus-V2.1](https://huggingface.co/IsValorum/Tiel-Coder-35B-A3B-APEX-I-MiniPlus-V2.1-GGUF)** — a specialist coding MoE tuned for agentic programming, iterative tool use, and implementation-heavy work. |
| > - **Best for:** Focused coding sessions, iterative debugging, and tool-driven implementation. |
| > |
| > These remain distinct model families and editions with their own behavior and empirical results. Pick by workload and intended alignment behavior rather than treating them as interchangeable quantization variants. |
| --- |
| |
| <a id="independent-benchmark"></a> |
| <a id="toc-01"></a> |
| ### 🏅 Independent Benchmark of the APEX-I-MiniPlus Family (Occamy V2 Reference) |
| |
| |
| > [!NOTE] |
| > **Occamy V2 Reference Notice:** **External report:** [zephel01 independently benchmarked Occamy V2](https://note.com/zephel01/n/n71d3d7e6b70c?hl=en). The benchmark below was performed on **Occamy-1.0 APEX-I-MiniPlus V2**, not on this specific Nex-N2.5 model. It is included as independent evidence of the broader APEX-I-MiniPlus quantization approach and hybrid MoE architecture. |
| |
| The **APEX-I-MiniPlus** quantization architecture powering this model was subjected to an extensive independent evaluation by Japanese AI researcher and evaluator [zephel01 (CoolZero)](https://note.com/zephel01/n/n71d3d7e6b70c?hl=en) on an **NVIDIA RTX 5090 (32GB)** workstation running `llama.cpp` CUDA `b11027` with FlashAttention (`-fa on -ctk q8_0 -ctv q8_0 -ngl 99`). |
| |
| The evaluation tested the APEX-I hybrid MoE engine across **348 unseeded trials** on SWE-bench style multi-file Python bug-fixing tasks with hidden `pytest` suites (`llmbench`): |
| |
| - **L6 Multi-File Code Generation (60 tasks):** |
| - **Context 32,768 (32K):** **93.3% Resolved** (46/60 tasks passed 5/5 consecutive trials; 20/20 on Easy–Hard). |
| - **Context 65,536 (65K):** **90.0% Resolved** (45/60 tasks passed 5/5 consecutive trials). |
| - **Match with 25–28 GB Models:** Matches or exceeds the resolution rate of full 25–28 GB models (such as `Ornith-1.5` and `Tiel-Coder` 35B-A3B) while consuming **over 10 GB less VRAM** (14.6 GB vs approx. 26 GB). |
| - **Extreme Context VRAM Scaling (The Hybrid DeltaNet SSM Advantage):** |
| - **32K Context:** **14.6 GB** total VRAM allocation. |
| - **65K Context:** **15.1 GB** total VRAM allocation (only **+0.5 GB VRAM** added when doubling context!). |
| - *Architectural Explanation:* Because 30 of the 40 layers utilize Linear Attention / DeltaNet SSM ($O(1)$ constant recurrence memory), only the 10 full-attention anchor layers expand the KV cache. This proves empirically that **65,536 context runs 100% in VRAM on consumer 16GB GPUs (RTX 4080 / RTX 5080)** without offloading to system RAM. |
| - **Measured Real-World Throughput:** Sustained single-stream generation of **approx. 247 – 251 tok/s** on NVIDIA RTX 5090. |
| |
| --- |
| |
| <a id="model-specifications"></a> |
| <a id="toc-02"></a> |
| ## Model Files & Specifications |
| |
| | File Name | File Size | Memory Footprint | BPW | Description | |
| | :--- | :--- | :--- | :--- | :--- | |
| | **`Nex-N2.5-mini.APEX-I-MiniPlus-V1.gguf`** | **`14.56 GB` (`13.56 GiB`)** | `13.56 GiB` | **3.36 BPW** | Main language, reasoning, tool-use & computer-use model | |
| | **`mmproj-nex-agi_Nex-N2.5-mini-Q8_0.gguf`** | **`610 MB` (`582 MiB`)** | `582 MiB` | **8.50 BPW** | Dedicated `Q8_0` vision projector for GUI parsing & high-res image input | |
|
|
| - **Base Architecture:** `qwen35moe` (35.1B parameters, multimodal agentic MoE). |
| - **Core Strengths:** Autonomous computer-use, function calling, JSON schema compliance, high-resolution visual grounding. |
|
|
| --- |
|
|
| <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`. |
|
|
| 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, supporting efficient streaming on budget DDR4/DDR5 laptops. | |
| | **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. | |
| | **Normalization & Biases** | Often degraded | Standard | **`F32` uncompressed** | **Numerical Stability:** Prevents cumulative floating-point underflow/overflow across deep 40-layer computation. | |
| |
| --- |
| |
| <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. |
| - Rather than leaving users to search for external FP16 projectors (approx. 900 MB), this repository bundles the official projector quantized to **`Q8_0` (610 MB / 582 MiB)**. |
| - Delivers near-lossless visual recognition while saving VRAM. |
| |
| --- |
| |
| <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). |
| - **System Memory:** Standard **32 GB DDR4 @ 3200 MHz** holds the rest of the model. |
| - **Estimated Generation Speed:** **23 to 26+ tokens/second** sustained output! |
| - **Estimated Document Ingestion (Prefill):** **300 to 410+ tokens/second**. |
|
|
| --- |
|
|
| <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 | |
| | :--- | :--- | :--- | :--- | :--- | :--- | |
| | **32,512 (32k)** | `13.56 GiB` | `0.57 GiB` | `1.79 GiB` | **`15.92 GiB`** | Full offload on 24GB; 38/40 layers on 16GB | |
| | **64,512 (64k)** | `13.56 GiB` | `0.90 GiB` | `1.93 GiB` | **`16.39 GiB`** | Effortless fit on 24GB GPUs | |
| | **128,640 (128k)** | `13.56 GiB` | `1.55 GiB` | `2.20 GiB` | **`17.31 GiB`** | Effortless fit on 24GB GPUs | |
| | **262,144 (Full 256K)** | `13.56 GiB` | `2.90 GiB` | `2.78 GiB` | **`19.24 GiB`** | **FULL 256K NATIVE CONTEXT IN VRAM!** | |
| |
| --- |
| |
| <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 | |
| | :--- | :--- | :---: | :---: | : | |
| | **NVIDIA RTX 5080 / 5090 (Blackwell)** | Full GPU (`-ngl 99`) | **approx. 247 – 251 tok/s** | **2,800 – 3,900+ tok/s** | Empirically verified on RTX 5090 by zephel01 (Occamy V2 Reference) | |
| | **NVIDIA RTX 4090 (24GB GDDR6X)** | Full GPU (`-ngl 99`) + mmproj | **75 – 100+ tok/s** | **1,700 – 2,500+ tok/s** | Real-time computer-use screen analysis & tool calling | |
| | **NVIDIA RTX 3090 (24GB GDDR6)** | Full GPU (`-ngl 99`) + mmproj | **62 – 78+ tok/s** | **1,350 – 1,950+ tok/s** | Full 256k multi-modal context in dedicated VRAM | |
| | **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: |
| |
| | Hyperparameter | Value | Description / Creator Guidance | |
| | :--- | :---: | :--- | |
| | **Temperature** | `0.70` | Official nex-agi evaluation setting for coding (NexAU) and computer-use (NexCUA). | |
| | **Top-P** | `0.95` | Optimal balance between exploration and syntactic precision. | |
| | **Top-K** | `40` | Official top-k cutoff recommended in the model card for best generation quality. | |
| | **Context Compaction** | `Summary` | Creator recommends summary compaction when token usage exceeds 60% of context window. | |
| |
| > [!IMPORTANT] |
| > <a id="quantization-fidelity"></a> |
| > ### 🔍 Model Inherent Behavior vs. Quantization Fidelity Notice |
| > 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 |
|
|
| <a href="https://ko-fi.com/isvalorum"><img src="https://huggingface.co/spaces/IsValorum/MiniPlus-NanoPlus-Requests/resolve/main/assets/dance-gold-ship.gif" alt="Gold Ship dancing" width="128" align="right"></a> |
|
|
| If these MiniPlus or NanoPlus releases have been useful to you and you would like to support the work, you can do so voluntarily through https://ko-fi.com/isvalorum. Your contribution helps with evaluation, hosting, and future handcrafted quantizations. Every release will always remain free to download and use; there are no paywalled files, updates, or features. |
|
|
