Model Overview
Model Features
Model Capabilities
Use Cases
๐ phi-2 GGUF Models
Our latest quantization method offers precision-adaptive quantization for ultra-low-bit models, improving performance on Llama-3-8B while maintaining extreme memory efficiency.
๐ Quick Start
This README provides detailed information about phi-2 GGUF models, including quantization methods, model format selection, included files, and how to use the models.
โจ Features
- Ultra-Low-Bit Quantization: Our latest quantization method introduces precision-adaptive quantization for ultra-low-bit models (1 - 2 bit), with proven improvements on Llama - 3 - 8B.
- Multiple Model Formats: Offer various model formats (BF16, F16, Quantized Models) to meet different hardware and memory requirements.
- Suitable for Different Devices: Models are suitable for a wide range of devices, from high - performance GPUs to low - VRAM CPUs and ARM devices.
๐ฆ Installation
The README does not provide specific installation steps, so this section is skipped.
๐ป Usage Examples
The README does not provide specific code examples, so this section is skipped.
๐ Documentation
Ultra - Low - Bit Quantization with IQ - DynamicGate (1 - 2 bit)
Our latest quantization method introduces precision - adaptive quantization for ultra - low - bit models (1 - 2 bit), with benchmark - proven improvements on Llama - 3 - 8B. This approach uses layer - specific strategies to preserve accuracy while maintaining extreme memory efficiency.
Benchmark Context
All tests conducted on Llama - 3 - 8B - Instruct using:
- Standard perplexity evaluation pipeline
- 2048 - token context window
- Same prompt set across all quantizations
Method
- Dynamic Precision Allocation:
- First/Last 25% of layers โ IQ4_XS (selected layers)
- Middle 50% โ IQ2_XXS/IQ3_S (increase efficiency)
- Critical Component Protection:
- Embeddings/output layers use Q5_K
- Reduces error propagation by 38% vs standard 1 - 2bit
Quantization Performance Comparison (Llama - 3 - 8B)
Quantization | Standard PPL | DynamicGate PPL | ฮ PPL | Std Size | DG Size | ฮ Size | Std Speed | DG Speed |
---|---|---|---|---|---|---|---|---|
IQ2_XXS | 11.30 | 9.84 | -12.9% | 2.5G | 2.6G | +0.1G | 234s | 246s |
IQ2_XS | 11.72 | 11.63 | -0.8% | 2.7G | 2.8G | +0.1G | 242s | 246s |
IQ2_S | 14.31 | 9.02 | -36.9% | 2.7G | 2.9G | +0.2G | 238s | 244s |
IQ1_M | 27.46 | 15.41 | -43.9% | 2.2G | 2.5G | +0.3G | 206s | 212s |
IQ1_S | 53.07 | 32.00 | -39.7% | 2.1G | 2.4G | +0.3G | 184s | 209s |
Key:
- PPL = Perplexity (lower is better)
- ฮ PPL = Percentage change from standard to DynamicGate
- Speed = Inference time (CPU avx2, 2048 token context)
- Size differences reflect mixed quantization overhead
Key Improvements:
- ๐ฅ IQ1_M shows massive 43.9% perplexity reduction (27.46 โ 15.41)
- ๐ IQ2_S cuts perplexity by 36.9% while adding only 0.2GB
- โก IQ1_S maintains 39.7% better accuracy despite 1 - bit quantization
Tradeoffs:
- All variants have modest size increases (0.1 - 0.3GB)
- Inference speeds remain comparable (<5% difference)
When to Use These Models
๐ Fitting models into GPU VRAM โ Memory - constrained deployments โ Cpu and Edge Devices where 1 - 2bit errors can be tolerated โ Research into ultra - low - bit quantization
Choosing the Right Model Format
Selecting the correct model format depends on your hardware capabilities and memory constraints.
BF16 (Brain Float 16) โ Use if BF16 acceleration is available
- A 16 - bit floating - point format designed for faster computation while retaining good precision.
- Provides similar dynamic range as FP32 but with lower memory usage.
- Recommended if your hardware supports BF16 acceleration (check your device's specs).
- Ideal for high - performance inference with reduced memory footprint compared to FP32.
๐ Use BF16 if: โ Your hardware has native BF16 support (e.g., newer GPUs, TPUs). โ You want higher precision while saving memory. โ You plan to requantize the model into another format.
๐ Avoid BF16 if: โ Your hardware does not support BF16 (it may fall back to FP32 and run slower). โ You need compatibility with older devices that lack BF16 optimization.
F16 (Float 16) โ More widely supported than BF16
- A 16 - bit floating - point high precision but with less of range of values than BF16.
- Works on most devices with FP16 acceleration support (including many GPUs and some CPUs).
- Slightly lower numerical precision than BF16 but generally sufficient for inference.
๐ Use F16 if: โ Your hardware supports FP16 but not BF16. โ You need a balance between speed, memory usage, and accuracy. โ You are running on a GPU or another device optimized for FP16 computations.
๐ Avoid F16 if: โ Your device lacks native FP16 support (it may run slower than expected). โ You have memory limitations.
Quantized Models (Q4_K, Q6_K, Q8, etc.) โ For CPU & Low - VRAM Inference
Quantization reduces model size and memory usage while maintaining as much accuracy as possible.
- Lower - bit models (Q4_K) โ Best for minimal memory usage, may have lower precision.
- Higher - bit models (Q6_K, Q8_0) โ Better accuracy, requires more memory.
๐ Use Quantized Models if: โ You are running inference on a CPU and need an optimized model. โ Your device has low VRAM and cannot load full - precision models. โ You want to reduce memory footprint while keeping reasonable accuracy.
๐ Avoid Quantized Models if: โ You need maximum accuracy (full - precision models are better for this). โ Your hardware has enough VRAM for higher - precision formats (BF16/F16).
Very Low - Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)
These models are optimized for extreme memory efficiency, making them ideal for low - power devices or large - scale deployments where memory is a critical constraint.
-
IQ3_XS: Ultra - low - bit quantization (3 - bit) with extreme memory efficiency.
- Use case: Best for ultra - low - memory devices where even Q4_K is too large.
- Trade - off: Lower accuracy compared to higher - bit quantizations.
-
IQ3_S: Small block size for maximum memory efficiency.
- Use case: Best for low - memory devices where IQ3_XS is too aggressive.
-
IQ3_M: Medium block size for better accuracy than IQ3_S.
- Use case: Suitable for low - memory devices where IQ3_S is too limiting.
-
Q4_K: 4 - bit quantization with block - wise optimization for better accuracy.
- Use case: Best for low - memory devices where Q6_K is too large.
-
Q4_0: Pure 4 - bit quantization, optimized for ARM devices.
- Use case: Best for ARM - based devices or low - memory environments.
Summary Table: Model Format Selection
Model Format | Precision | Memory Usage | Device Requirements | Best Use Case |
---|---|---|---|---|
BF16 | Highest | High | BF16 - supported GPU/CPUs | High - speed inference with reduced memory |
F16 | High | High | FP16 - supported devices | GPU inference when BF16 isn't available |
Q4_K | Medium Low | Low | CPU or Low - VRAM devices | Best for memory - constrained environments |
Q6_K | Medium | Moderate | CPU with more memory | Better accuracy while still being quantized |
Q8_0 | High | Moderate | CPU or GPU with enough VRAM | Best accuracy among quantized models |
IQ3_XS | Very Low | Very Low | Ultra - low - memory devices | Extreme memory efficiency and low accuracy |
Q4_0 | Low | Low | ARM or low - memory devices | llama.cpp can optimize for ARM devices |
Included Files & Details
phi-2-bf16.gguf
- Model weights preserved in BF16.
- Use this if you want to requantize the model into a different format.
- Best if your device supports BF16 acceleration.
phi-2-f16.gguf
- Model weights stored in F16.
- Use if your device supports FP16, especially if BF16 is not available.
phi-2-bf16-q8_0.gguf
- Output & embeddings remain in BF16.
- All other layers quantized to Q8_0.
- Use if your device supports BF16 and you want a quantized version.
phi-2-f16-q8_0.gguf
- Output & embeddings remain in F16.
- All other layers quantized to Q8_0.
phi-2-q4_k.gguf
- Output & embeddings quantized to Q8_0.
- All other layers quantized to Q4_K.
- Good for CPU inference with limited memory.
phi-2-q4_k_s.gguf
- Smallest Q4_K variant, using less memory at the cost of accuracy.
- Best for very low - memory setups.
phi-2-q6_k.gguf
- Output & embeddings quantized to Q8_0.
- All other layers quantized to Q6_K .
phi-2-q8_0.gguf
- Fully Q8 quantized model for better accuracy.
- Requires more memory but offers higher precision.
phi-2-iq3_xs.gguf
- IQ3_XS quantization, optimized for extreme memory efficiency.
- Best for ultra - low - memory devices.
phi-2-iq3_m.gguf
- IQ3_M quantization, offering a medium block size for better accuracy.
- Suitable for low - memory devices.
phi-2-q4_0.gguf
- Pure Q4_0 quantization, optimized for ARM devices.
- Best for low - memory environments.
- Prefer IQ4_NL for better accuracy.
Testing the Models
If you find these models useful
โค Please click "Like" if you find this useful! Help me test my AI - Powered Network Monitor Assistant with quantum - ready security checks: ๐ Free Network Monitor
๐ฌ How to test:
- Click the chat icon (bottom right on any page)
- Choose an AI assistant type:
TurboLLM
(GPT - 4 - mini)FreeLLM
(Open - source)TestLLM
(Experimental CPU - only)
What Iโm Testing
Iโm pushing the limits of small open - source models for AI network monitoring, specifically:
- Function calling against live network services
- How small can a model go while still handling:
- Automated Nmap scans
- Quantum - readiness checks
- Metasploit integration
๐ก TestLLM โ Current experimental model (llama.cpp on 6 CPU threads):
- โ Zero - configuration setup
- โณ 30s load time (slow inference but no API costs)
- ๐ง Help wanted! If youโre into edge - device AI, letโs collaborate!
Other Assistants
๐ข TurboLLM โ Uses gpt - 4 - mini for:
- Real - time network diagnostics
- Automated penetration testing (Nmap/Metasploit)
- ๐ Get more tokens by downloading our Free Network Monitor Agent
๐ต HugLLM โ Open - source models (โ8B params):
- 2x more tokens than TurboLLM
- AI - powered log analysis
- ๐ Runs on Hugging Face Inference API
Example AI Commands to Test
"Give me info on my websites SSL certificate"
"Check if my server is using quantum safe encyption for communication"
"Run a quick Nmap vulnerability test"
Model Summary
Phi - 2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as [Phi - 1.5](https://huggingface.co/microsoft/phi - 1.5), augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi - 2 showcased a nearly state - of - the - art performance among models with less than 13 billion parameters.
Our model hasn't been fine - tuned through reinforcement learning from human feedback. The intention behind crafting this open - source model is to provide the research community with a non - restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.
How to Use
Phi - 2 has been integrated in the transformers
version 4.37.0, please ensure that you are using a version equal or higher than it.
Phi - 2 is known for having an attention overflow issue (with FP16). If you are facing this issue, please enable/disable autocast on the PhiAttention.forward() function.
Intended Uses
Given the nature of the training data, the Phi - 2 model is best suited for prompts using the QA format, the chat format, and the code format.
QA Format:
You can provide the prompt as a standalone question as follows:
Write a detailed analogy between mathematics and a lighthouse.
where the model generates the text after "." .
To encourage the model to write more concise answers, you can also try the following QA format using "Instruct:
Instruct: Write a detailed analogy between mathematics and a lighthouse.
Output: Mathematics is like a lighthouse. Just as a lighthouse guides ships safely to shore, mathematics provides a guiding light in the world of numbers and logic. It helps us navigate through complex p
๐ง Technical Details
The README does not provide specific technical details that meet the requirement of over 50 words, so this section is skipped.
๐ License
This project is licensed under the MIT License.

