README.md

---
pipeline_tag: text-generation
inference: false
license: apache-2.0
library_name: transformers
tags:
- language
- aquif
- text-generation-inference
- reasoning
- math
- coding
- frontier
- aquif-3.5
language:
- en
- de
- it
- pt
- fr
- hi
- es
- th
- zh
- ja
---

# aquif-3.5-Plus & aquif-3.5-Max

The pinnacle of the aquif-3.5 series, released November 3rd, 2025. These models bring advanced reasoning capabilities and unprecedented context windows to achieve state-of-the-art performance for their respective categories.

**aquif-3.5-Plus** combines hybrid reasoning with interchangeable thinking modes, offering flexibility for both speed-optimized and reasoning-intensive applications.

**aquif-3.5-Max** represents frontier model capabilities with reasoning-only architecture, delivering exceptional performance across all benchmark categories.

## Model Repository Links

| Model | HuggingFace Repository |
|-------|----------------------|
| aquif-3.5-Plus | [aquiffoo/aquif-3.5-Plus](https://huggingface.co/aquiffoo/aquif-3.5-Plus) |
| aquif-3.5-Max | [aquiffoo/aquif-3.5-Max](https://huggingface.co/aquiffoo/aquif-3.5-Max) |

## Model Overview

| Model | Total (B) | Active Params (B) | Reasoning | Context Window | Thinking Modes |
|-------|-----------|-------------------|-----------|-----------------|----------------|
| aquif-3.5-Plus | 30.5 | 3.3 | ✅ Hybrid | 1M | ✅ Interchangeable |
| aquif-3.5-Max | 42.4 | 3.3 | ✅ Reasoning-Only | 1M | Reasoning-Only |

## Model Details

### aquif-3.5-Plus (Hybrid Reasoning with Interchangeable Modes)

A breakthrough hybrid reasoning model offering unprecedented flexibility. Toggle between thinking and non-thinking modes to optimize for your specific use case—maintain reasoning capabilities when needed, or prioritize speed for time-sensitive applications.

## Artificial Analysis Intelligence Index (AAII) Benchmarks

### Core Performance Metrics

| Benchmark | aquif-3.5-Plus (Non-Reasoning) | aquif-3.5-Plus (Reasoning) | aquif-3.5-Max |
|-----------|--------------------------------|----------------------------|----------------|
| MMLU-Pro | 80.2 | 82.8 | 85.4 |
| GPQA Diamond | 72.1 | 79.7 | 83.2 |
| AIME 2025 | 64.7 | 90.3 | 94.6 |
| LiveCodeBench | 50.5 | 76.4 | 81.6 |
| Humanity's Last Exam | 4.3 | 12.1 | 15.6 |
| TAU2-Telecom | 34.2 | 41.5 | 51.3 |
| IFBench | 39.3 | 54.3 | 65.4 |
| TerminalBench-Hard | 10.1 | 15.2 | 23.9 |
| AA-LCR | 30.4 | 59.9 | 61.2 |
| SciCode | 29.5 | 35.7 | 40.9 |
| **AAII Composite Score** | **42 (41.53)** | **55 (54.79)** | **60 (60.31)** |

### Comparable Models by Configuration

**aquif-3.5-Plus (Non-Reasoning) — AAII 42**

| Model | AAII Score |
|-------|-----------|
| GPT-5 mini | 42 |
| Claude Haiku 4.5 | 42 |
| Gemini 2.5 Flash Lite 2509 | 42 |
| **aquif-3.5-Plus (Non-Reasoning)** | **42** |
| DeepSeek V3 0324 | 41 |
| Qwen3 VL 32B Instruct | 41 |
| Qwen3 Coder 480B A35B | 42 |

**aquif-3.5-Plus (Reasoning) — AAII 55**

| Model | AAII Score |
|-------|-----------|
| GLM-4.6 | 56 |
| Gemini 2.5 Flash 2509 | 54 |
| Claude Haiku 4.5 | 55 |
| **aquif-3.5-Plus (Reasoning)** | **55** |
| Qwen3 Next 80B A3B | 54 |

**aquif-3.5-Max — AAII 60**

| Model | AAII Score |
|-------|-----------|
| Gemini 2.5 Pro | 60 |
| Grok 4 Fast | 60 |
| **aquif-3.5-Max** | **60** |
| MiniMax-M2 | 61 |
| gpt-oss-120B high | 61 |
| GPT-5 mini | 61 |
| DeepSeek-V3.1-Terminus | 58 |
| Claude Opus 4.1 | 59 |

## Key Features

**Massive Context Windows**: Both models support up to 1M tokens, enabling analysis of entire codebases, research papers, and extensive conversation histories without truncation.

**Efficient Architecture**: Despite offering frontier-level performance, both models maintain exceptional efficiency through optimized mixture-of-experts design and active parameter count of just 3.3B.

**Flexible Reasoning (Plus Only)**: aquif-3.5-Plus provides interchangeable thinking modes—enable reasoning for complex problems, disable for faster inference on straightforward tasks.

**Multilingual Support**: Native support across English, German, Italian, Portuguese, French, Hindi, Spanish, Thai, Chinese, and Japanese.

## Usage Recommendations

**aquif-3.5-Plus:**
- Complex reasoning requiring flexibility between speed and depth
- Scientific analysis and mathematical problem-solving with thinking enabled
- Rapid-response applications with thinking disabled
- Code generation and review
- Multilingual applications up to 1M token contexts

**aquif-3.5-Max:**
- Frontier-level problem-solving without compromise
- Advanced research and scientific computing
- Competition mathematics and algorithmic challenges
- Comprehensive code analysis and generation
- Complex multilingual tasks requiring maximum reasoning capability

## Setting Thinking Mode (aquif-3.5-Plus)

Toggle between thinking and non-thinking modes by modifying the chat template:

```
set thinking = true    # Enable reasoning mode
set thinking = false   # Disable thinking mode (faster inference)
```

Simply set the variable in your chat template before inference to switch modes. No model reloading required.

## Technical Specifications

Both models support:
- BF16 and FP16 precision
- Mixture of Experts architecture optimizations
- Efficient attention mechanisms with optimized KV caching
- Up to 1M token context window
- Multi-head attention with sparse routing

## Performance Highlights

**aquif-3.5-Plus** achieves 82.3% average benchmark performance in thinking mode, surpassing models with 2-4x more total parameters. Non-thinking mode maintains competitive 66.9% performance for latency-sensitive applications.

**aquif-3.5-Max** reaches 86.2% average performance, matching or exceeding frontier models while maintaining 42.4B total parameters—an extraordinary efficiency breakthrough.

## Acknowledgements

- **Qwen Team**: Base architecture contributions
- **Meta Llama Team**: Core model foundations
- **Hugging Face**: Model hosting and training infrastructure

## License

This project is released under the Apache 2.0 License. See LICENSE file for details.

---

*Made in 🇧🇷*

© 2025 aquif AI. All rights reserved.