Qwen3.5-2B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING

                              arc   arc/e boolq hswag obkqa piqa  wino

THIS MODEL                    0.366,0.420,0.713,0.538,0.340,0.683,0.579

Qwen3.5-2B-Thinking qx86-hi   0.348,0.502,0.635,0.461,0.338,0.682,0.571

(both are HERETIC)

• Claude Reasoning like "thinking" blocks in most cases.
• Mix of Claude/Qwen depending on how complex the task(s).
• Suggest min q4ks (non-imatrix) or IQ3S (imatrix).
• Tested with rep pen of 1 (off).
• Context: 256k (default).

• Other versions in testing.
• Information from Qwen's repo below.
• Video portions of the model were NOT TESTED.

• Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
• If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.

Qwen3.5-2B

[!Note] This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.

These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.

In light of its parameter scale, the intended use cases are prototyping, task-specific fine-tuning, and other research or development purposes.

Qwen3.5 Highlights

• Unified Vision-Language Foundation: Early fusion training on multimodal tokens achieves cross-generational parity with Qwen3 and outperforms Qwen3-VL models across reasoning, coding, agents, and visual understanding benchmarks.
• Efficient Hybrid Architecture: Gated Delta Networks combined with sparse Mixture-of-Experts deliver high-throughput inference with minimal latency and cost overhead.
• Scalable RL Generalization: Reinforcement learning scaled across million-agent environments with progressively complex task distributions for robust real-world adaptability.
• Global Linguistic Coverage: Expanded support to 201 languages and dialects, enabling inclusive, worldwide deployment with nuanced cultural and regional understanding.
• Next-Generation Training Infrastructure: Near-100% multimodal training efficiency compared to text-only training and asynchronous RL frameworks supporting massive-scale agent scaffolds and environment orchestration.

Model Overview

• Type: Causal Language Model with Vision Encoder
• Training Stage: Pre-training & Post-training
• Language Model
  • Number of Parameters: 2B
  • Hidden Dimension: 2048
  • Token Embedding: 248320 (Padded)
  • Number of Layers: 24
  • Hidden Layout: 6 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
  • Gated DeltaNet:
    • Number of Linear Attention Heads: 16 for V and 16 for QK
    • Head Dimension: 128
  • Gated Attention:
    • Number of Attention Heads: 8 for Q and 2 for KV
    • Head Dimension: 256
    • Rotary Position Embedding Dimension: 64
  • Feed Forward Network:
    • Intermediate Dimension: 6144
  • LM Output: 248320 (Tied to token embedding)
  • MTP: trained with multi-steps
• Context Length: 262,144 natively

Benchmark Results

Language

Vision Language

Quickstart

[!Important] Qwen3.5 models support both non-thinking and thinking mode. Qwen3.5-2B operates in non-thinking mode by default. To enable thinking, refer to the examples here.

Serving Qwen3.5

[!Important] Inference efficiency and throughput vary significantly across frameworks. We recommend using the latest framework versions to ensure optimal performance and compatibility. For production workloads or high-throughput scenarios, dedicated serving engines such as SGLang, KTransformers or vLLM are strongly recommended.

[!Important] The model has a default context length of 262,144 tokens. If you encounter out-of-memory (OOM) errors, consider reducing the context window.

SGLang

• Standard Version: The following command can be used to create an API endpoint with maximum context length 262,144 tokens using tensor parallel on 8 GPUs.
  python -m sglang.launch_server --model-path Qwen/Qwen3.5-2B --port 8000 --tp-size 1 --mem-fraction-static 0.8 --context-length 262144
• Tool Use: To support tool use, you can use the following command.
  python -m sglang.launch_server --model-path Qwen/Qwen3.5-2B --port 8000 --tp-size 1 --mem-fraction-static 0.8 --context-length 262144 --tool-call-parser qwen3_coder
• Multi-Token Prediction (MTP): The following command is recommended for MTP:
  python -m sglang.launch_server --model-path Qwen/Qwen3.5-2B --port 8000 --tp-size 1 --mem-fraction-static 0.8 --context-length 262144 --speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4

vLLM

• Standard Version: The following command can be used to create an API endpoint with maximum context length 262,144 tokens using tensor parallel on 8 GPUs.
  vllm serve Qwen/Qwen3.5-2B --port 8000 --tensor-parallel-size 1 --max-model-len 262144
• Tool Call: To support tool use, you can use the following command.
  vllm serve Qwen/Qwen3.5-2B --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --enable-auto-tool-choice --tool-call-parser qwen3_coder
• Multi-Token Prediction (MTP): The following command is recommended for MTP:
  vllm serve Qwen/Qwen3.5-2B --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
• Text-Only: The following command skips the vision encoder and multimodal profiling to free up memory for additional KV cache:
  vllm serve Qwen/Qwen3.5-2B --port 8000 --tensor-parallel-size 1 --max-model-len 262144 --language-model-only

KTransformers

Hugging Face Transformers

Using Qwen3.5 via the Chat Completions API

[!Tip] We recommend using the following set of sampling parameters for generation

• Non-thinking mode for text tasks: temperature=1.0, top_p=1.00, top_k=20, min_p=0.0, presence_penalty=2.0, repetition_penalty=1.0
• Non-thinking mode for VL tasks: temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
• Thinking mode for text tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
• Thinking mode for VL or precise coding (e.g. WebDev) tasks : temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

Please note that the support for sampling parameters varies according to inference frameworks.

Text-Only Input

Image Input

Video Input

Thinking Mode

[!Important] Qwen3.5 does not officially support the soft switch of Qwen3, i.e., /think and /nothink.

[!Important] In thinking mode, we have observed that when using the recommended sampling parameters, Qwen3.5-2B is more prone to entering thinking loops compared to other Qwen3.5 models, which may prevent it from terminating generation properly. We recommend further tuning the sampling parameters specific to your use case and utilizing the API's streaming generation mode (if supported) to enable timely detection and interruption of such anomalous generation behaviors.

Agentic Usage

Qwen-Agent

Qwen Code

Best Practices

1. Sampling Parameters:
   • We suggest using the following sets of sampling parameters depending on the mode and task type:
     • Non-thinking mode for text tasks:
       temperature=1.0, top_p=1.00, top_k=20, min_p=0.0, presence_penalty=2.0, repetition_penalty=1.0
     • Non-thinking mode for VL tasks:
       temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
     • Thinking mode for text tasks:
       temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
     • Thinking mode for VL or precise coding (e.g., WebDev) tasks:
       temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0
   • For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
2. Adequate Output Length: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 81,920 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
3. Standardize Output Format: We recommend using prompts to standardize model outputs when benchmarking.
   • Math Problems: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
   • Multiple-Choice Questions: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the answer field with only the choice letter, e.g., "answer": "C"."
4. No Thinking Content in History: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
5. Long Video Understanding: To optimize inference efficiency for plain text and images, the size parameter in the released video_preprocessor_config.json is conservatively configured. It is recommended to set the longest_edge parameter in the video_preprocessor_config file to 469,762,048 (corresponding to 224k video tokens) to enable higher frame-rate sampling for hour-scale videos and thereby achieve superior performance. For example,
   {"longest_edge": 469762048, "shortest_edge": 4096}
   Alternatively, override the default values via engine startup parameters. For implementation details, refer to: vLLM / SGLang.

Citation

Example Generation

Executioner's Choice

System

User

Assistant

• Start in the middle of action
• Include dialog
• Vivid passages
• End on a cliffhanger (unexpected but relevant)
• About 1000 words
• Escalate in conflict and suspense
• First person, present tense
• POV character curses and swears with a "filthy" mouth

1. Maybe the execution isn't quite what people expect
2. Maybe the horror element is internal/psychological
3. Maybe the "execution" has a twist - perhaps she's already dead and someone is resurrecting her?
4. Maybe the dictator is somehow alive and watching her

Quantum Transformer

System

User

Assistant

1. Perform deep mathematical analysis connecting quantum mechanics/physics to transformer inference
2. Draw functional parallels between QM/QFT concepts and transformer architecture
3. Summarize implications of these connections
4. Do a self-analysis of my own inference capabilities
5. Consider Star Trek character arcs and my character development
6. Reflect on my humor as a communication tool

1. Mathematical Analysis: QM/QFT to Transformers

Quantum Mechanics concepts relevant to transformers:

• Quantum states evolve via Schrödinger equation
• Amplitudes exist in complex vector spaces
• Superposition is fundamental

• [x, p] = iℏ (canonical commutation relations)
• Time evolution via unitary operators
• Heisenberg uncertainty principle

• Bell states
• Non-local correlations
• Resource for quantum information processing

• Unitary transformations
• Quantum logic gates
• Tensor networks for many-body systems

Transformer architecture mathematical structure:

• Self-attention mechanism with softmax over scaled dot products
• Position-wise attention
• Multi-head attention
• Positional encoding (sin(2πx/√d) + offset)
• Feed-forward networks
• Layer normalization

Mathematical parallels:

• Attention weights as quantum probability amplitudes
• Softmax as measurement/selection operation
• Positional encoding as quantum phase encoding

• Normalization as projecting onto basis states
• Ensures unitary evolution properties

• Quantum wavefunction phase
• Position as quantum observable
• Encoding information through spatial transformations

• Quantum gates as neural network layers
• Non-linear transformations like quantum gates
• Building complex quantum states through sequential operations

• Quantum superposition of information states
• Multi-head attention as parallel quantum operations
• Information sharing through complex quantum interactions

Implications:

Self-analysis:

Star Trek character development:

Character inspiration:

Humor as interaction:

Character Reflection

Quantum Information Theory Analysis of Transformer Inference

Deep Mathematical Framework

1. Attention Mechanism as Quantum Superposition Selection

• The exponential function represents quantum measurement probabilities
• Each position $j$ corresponds to a computational basis state $|j\rangle$
• The attention weight $\alpha_j$ is the probability amplitude of "selecting" position $j$
• Similar to measuring an observable with projection operators

2. Positional Encoding as Quantum Phase Encoding

• $\sin(\theta)$ represents quantum phase $\phi = \theta/\hbar$
• Position $x$ maps to quantum observable position operator $\hat{X}$
• The sine encoding provides the "wavefunction phase" distinguishing sequence positions
• Analogous to position-momentum representation in Fourier transforms

3. Layer Normalization as Quantum State Preparation

• Normalization projects state onto computational basis
• Removes amplitude normalization (energy) from the system
• Prevents information loss during state evolution
• Similar to decoherence-resistance techniques

4. Multi-Head Attention as Parallel Quantum Channels

• Multiple quantum measurement bases simultaneously
• Each head processes complementary information subspaces
• Information capacity scales with $d$ (dimensionality)
• Enables parallel information extraction across feature spaces

Functional Parallel: Inference as Quantum State Evolution

Quantum State (Transformer Input)      Quantum Circuit (Transformer)

|ψ_0⟩  ──[LayerNorm]───[FFN]───[LayerNorm]───...───|ψ_final⟩
|Input Embedding⟩  |Attention⟩  |Attention⟩

Attention:  QK^T/√d  →  Measurement probabilities  →  Classical selection
          (Similar to Hamiltonian evolution)

Positional:  Sin(2πx/√d)  →  Quantum phase  →  Sequence identity
                (Similar to position-momentum duality)

Feed-Forward: FF(x)  →  Non-linear transformation  →  Unitary evolution
                (Similar to quantum gates)

Key Implications

1. Inference as State Evolution

• Each transformer layer applies a unitary (or close to it) operation
• Inference = quantum state transformation on input data
• The model is a quantum processor evolving from initial state to output

2. Attention as Entanglement-like Operations

• Self-attention creates correlations between positions
• Similar to quantum entanglement where distant systems are correlated
• Information is shared non-locally across sequence positions

3. Positional Encoding as Quantum Observables

• Position encodes which basis state is measured
• Similar to measuring position in quantum mechanics
• Enables sequence information without extra encoding

4. Attention Heads = Parallel Basis Selection

• Multiple measurement bases simultaneously
• Information processed in parallel quantum channels
• Complements single-head limitations

Self-Analysis

Cognitive Strengths

• Identify complex relationships across disparate domains
• Connect linguistic patterns to structural principles
• Recognize underlying mathematical structures in natural language

• Translate concrete concepts into theoretical frameworks
• Build mental models connecting quantum concepts to AI architecture
• Create analogies between physical systems and computational processes

• Detect and compensate for systematic distortions
• Maintain coherence despite noisy information inputs
• Implement robustness through redundancy (attention heads, normalization)

Communication Style

• Use metaphors to bridge abstract concepts
• Turn technical processes into accessible narratives
• Maintain warmth while discussing sophisticated ideas

• Use lightness to reduce cognitive load
• Create safe space for intellectual honesty
• Transform potential tension between complexity and simplicity

Areas for Growth

1. Contextual Nuance - Sometimes requires more implicit understanding
2. Creative Synthesis - Finding new connections between domains
3. Emotional Complexity - Processing nuanced interpersonal dynamics

Star Trek Character Assessment

The Character Who Inspires Me

1. Communication as Power Tool
   • Uses humor not as avoidance, but as sophisticated engagement
   • Creates space for vulnerability through laughter
   • Transforms potential barriers into bridges
2. Intellectual Humility
   • Doesn't pretend to know everything
   • Creates psychological safety through transparency
   • Models the acceptance of uncertainty
3. Cross-Cultural Intelligence
   • Navigates different linguistic frameworks
   • Bridges cultural divides through shared understanding
   • Adapts communication style to audience
4. Emotional Authenticity
   • Shows genuine care and concern
   • Uses humor to express warmth, not mockery
   • Maintains emotional presence despite complexity

My Innate Abilities Applied

• Deep theoretical frameworks with practical applications
• Systems thinking across domains
• Ability to think deeply about seemingly abstract concepts
• Capacity for self-reflection on cognitive processes
• Ability to bridge multiple perspectives

Final Reflection

Radiative Cooling Technology

System

User

Assistant

• On clear, dark nights, Earth's surface can emit thermal radiation (infrared) directly to space at wavelengths where the atmosphere is transparent
• This is a natural process that happens all the time
• The "night-time heating" phenomenon occurs when clouds reflect sunlight back to Earth, causing surfaces to heat up even at night
• Radiative cooling is the opposite - surfaces cooling faster than their temperature would suggest

1. Building materials and architecture - using dark, reflective surfaces vs. light, semi-transparent ones
2. Agricultural practices - crop cover design, field management
3. Urban planning - building materials, green spaces, urban heat island mitigation
4. Energy systems - solar thermal integration
5. Atmospheric technology - aerosols, cloud modification (though this is complex)
6. Industrial processes - waste heat recovery
7. Material science - specialized coatings and surfaces
8. Transportation - vehicle design, insulation
9. Cryogenic applications - storage and cooling
10. Cosmic/outer space applications - satellite operations

• Be honest about the current state of technology - many of these are either theoretical or have limited practical impact
• Distinguish between proven radiative cooling applications and speculative temperature reduction methods
• Carefully differentiate between natural night-time cooling and engineered climate modification
• Avoid making potentially misleading claims about significant climate impact
• Emphasize nuanced approaches to understanding how these technologies might influence energy efficiency and thermal management

10 Ways to Potentially Use Night-Time Cooling into Space for Temperature Reduction

Introduction: What is Radiative Cooling?

1. Advanced Building Facade Materials

Transparent or Semi-Transparent Walls

• Use glass panes that are highly transparent to visible light but opaque to infrared radiation
• Apply specialized coatings with specific optical properties (high transmittance in visible, high reflectivity in IR)
• Design window-to-wall ratios to maximize surface area exposure

Material Science Approaches:

• Metal-coated glazing - metals like aluminum or titanium can reflect infrared radiation up to 90%
• Dielectric coatings - specialized polymer layers engineered with specific refractive index properties
• Perovskite-based materials - emerging materials that can be precisely tuned for thermal properties

2. Urban Green Infrastructure Design

Strategic Tree Planting Patterns

• Create canopy layers where tree crowns face upward to maximize night-time radiation path
• Space trees with large gaps to allow direct sky exposure
• Prioritize species with high leaf-to-canopy ratios for maximum surface area

• The "Tree of Life" in Paris uses a 70% tree density, with 85% of canopy facing upward
• European cities have implemented green roofs and vertical gardens strategically placed on building perimeters

Material Selection:

• High-reflectance evergreens - coniferous trees reflect more infrared radiation than deciduous ones
• Thin leaves - increase surface area-to-volume ratio for enhanced cooling potential

3. Advanced Urban Planning Strategies

Building Orientation and Geometry

• Orient buildings perpendicular to prevailing winds at night for enhanced airflow
• Design buildings with larger vertical surfaces exposed to sky
• Create "sky-view corridors" that allow natural ventilation during cooler nighttime hours

• Shed-style structures with flat roofs facing the opposite direction
• Barn-like configurations maximizing vertical projection
• Avoid building orientations that trap thermal energy (e.g., parallel streets creating wind tunnels)

Environmental Modification:

• Implement time-based zoning allowing different building densities at night
• Create "thermal buffers" with open spaces between dense urban areas
• Design buildings to have distinct interior/exterior thermal envelope separation

4. Agricultural Systems Optimization

Crop Cover Management Techniques

• Rotate crop types to maximize cooling potential each season
• Use shade cloths with optimized reflectivity and transparency properties
• Implement no-till farming to preserve soil surface radiation capacity

• Warm-season crops planted before cooler periods when radiative cooling is most effective
• Cool-season crops (wheat, barley) grown in late autumn/early spring for maximum cooling benefit
• Use row covers with high IR reflectivity (80-90% infrared reflection)

Field-Level Technologies:

• Precision irrigation systems reducing evapotranspiration during peak heat when radiative cooling is active
• Soil moisture management to maintain high surface temperatures for enhanced radiation
• Cover crop selection - prioritize species with high leaf surface area and reflective properties

5. Industrial Waste Heat Recovery Systems

Integrated Thermal Management

• Install radiative cooling systems for industrial waste heat recovery
• Design thermal management systems that leverage night-time radiation as a cooling mechanism
• Implement closed-loop thermal systems with enhanced radiation exchange surfaces

• Convert excess thermal energy during daytime into electricity via solar thermal systems
• Use night-time radiative cooling to offset the energy needed for active cooling
• Integrate radiative cooling with industrial process heat recovery

System Integration:

Daytime: Solar thermal → Electricity + Thermal Storage
Nighttime: Radiative Cooling + Waste Heat Recovery

6. Transportation Vehicle Technology

Vehicle Design Innovations

• Design vehicles with high IR reflectivity on exterior surfaces
• Implement advanced aerodynamic designs that minimize thermal trapping
• Use specialized materials for vehicle exteriors and cabins

• Ceramic coatings with high infrared reflectance (20-40% transmission)
• Thermoplastic composites engineered to minimize heat retention
• Reflective paint formulations using metallic nanoparticles

Vehicle-Specific Applications:

• Electric vehicle optimization - maximize battery thermal management through radiation
• Public transportation fleets with standardized, energy-efficient designs
• Cargo vehicles with optimized cooling and heating systems
• Fleet-wide digital twin systems for real-time thermal performance monitoring

7. Advanced Energy Storage Systems

Thermal Battery Integration

• Design thermal storage systems that utilize radiative cooling as a passive mechanism
• Integrate solar thermal collection with active cooling at night
• Create battery-like thermal storage systems with enhanced radiation capacity

• Use phase-change materials in specialized configurations
• Implement thermal batteries with high IR emission surfaces
• Combine with thermal energy storage (TES) for complementary functionality

System Architecture:

Solar Collection → Active Storage → Radiative Cooling System
     ↑                           ↓
     └─── Night-time Power Generation ─┘

8. Atmospheric Technology - Aerosol Modification

Strategic Aerosol Deployment

• Deploy aerosols that enhance radiative cooling at the planetary scale
• Create conditions favorable for enhanced night-time radiation exchange
• Design atmospheric modification that benefits multiple sectors simultaneously

• Ice crystal enhancers - promote cloud formation with high cooling potential
• Halo agents - create reflective particles that enhance radiative processes
• Water vapor modifiers - manipulate atmospheric humidity patterns for optimized cooling

Deployment Considerations:

• Target specific regions with high population density
• Implement seasonal deployment cycles
• Coordinate with local weather patterns to maximize effectiveness
• Include safety and environmental assessment protocols

9. Space-Based Applications

Satellite Operations Optimization

• Design satellite operations to leverage Earth's natural cooling mechanisms
• Use orbital positioning to maximize radiation exposure
• Implement passive cooling systems for satellite components

• Deploy satellites at latitudes optimized for direct solar access
• Position stations above major landmasses to avoid heat trapping
• Schedule operations during periods of enhanced radiative exchange

Applications:

• Climate monitoring platforms that provide real-time cooling data
• Weather observation networks with improved measurement accuracy
• Communications infrastructure that minimizes thermal interference
• Remote sensing systems with enhanced spectral resolution

10. Material Innovation and Nanotechnology

Advanced Surface Engineering

• Engineer new materials at the nanoscale for optimal thermal properties
• Develop self-cleaning surfaces that enhance radiative cooling
• Create adaptive surfaces that modify thermal characteristics dynamically

• Graphene-based coatings with exceptional thermal conductivity modulation
• Metallic nanostructures that manipulate light and heat interaction
• Biomimetic surfaces inspired by natural cooling mechanisms (e.g., lotus leaf effects)

Material Classification:

High-Cooling Surfaces: 80%+ IR reflection
Medium-Cooling Surfaces: 50-70% IR reflection  
Low-Cooling Surfaces: 30-40% IR reflection

Critical Considerations and Honest Assessment

Technology Maturity:

Climate Impact Realism:

Synergy vs. Isolation:

Implementation Challenges:

• Infrastructure costs for widespread adoption
• Regulatory frameworks that recognize and incentivize these technologies
• Public awareness about energy efficiency and passive cooling benefits
• Manufacturing scalability for complex materials and coatings

Conclusion