gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Instruct-mxfp8-mlx

509
license:apache-2.0
by
nightmedia
Other
OTHER
4B params
New
509 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
9GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
4GB+ RAM

Training Data Analysis

🟡 Average (4.3/10)

Researched training datasets used by gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Instruct-mxfp8-mlx with quality assessment

Specialized For

general
science
multilingual
reasoning

Training Datasets (3)

common crawl
🔴 2.5/10
general
science
Key Strengths
  • •Scale and Accessibility: At 9.5+ petabytes, Common Crawl provides unprecedented scale for training d...
  • •Diversity: The dataset captures billions of web pages across multiple domains and content types, ena...
  • •Comprehensive Coverage: Despite limitations, Common Crawl attempts to represent the broader web acro...
Considerations
  • •Biased Coverage: The crawling process prioritizes frequently linked domains, making content from dig...
  • •Large-Scale Problematic Content: Contains significant amounts of hate speech, pornography, violent c...
wikipedia
🟡 5/10
science
multilingual
Key Strengths
  • •High-Quality Content: Wikipedia articles are subject to community review, fact-checking, and citatio...
  • •Multilingual Coverage: Available in 300+ languages, enabling training of models that understand and ...
  • •Structured Knowledge: Articles follow consistent formatting with clear sections, allowing models to ...
Considerations
  • •Language Inequality: Low-resource language editions have significantly lower quality, fewer articles...
  • •Biased Coverage: Reflects biases in contributor demographics; topics related to Western culture and ...
arxiv
🟡 5.5/10
science
reasoning
Key Strengths
  • •Scientific Authority: Peer-reviewed content from established repository
  • •Domain-Specific: Specialized vocabulary and concepts
  • •Mathematical Content: Includes complex equations and notation
Considerations
  • •Specialized: Primarily technical and mathematical content
  • •English-Heavy: Predominantly English-language papers

Explore our comprehensive training dataset analysis

View All Datasets

Code Examples

gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Instruct-mxfp8-mlxbrainwaves
arc   arc/e boolq hswag obkqa piqa  wino
bf16     0.434,0.554,0.831
mxfp8    0.444,0.553,0.831,0.646,0.412,0.751,0.630
q8-hi    0.436,0.558,0.833,0.642,0.422,0.755,0.631
q8       0.439,0.556,0.829,0.644,0.418,0.755,0.620
qx86-hi  0.434,0.562,0.827,0.642,0.428,0.756,0.631
qx64-hi  0.422,0.531,0.813,0.623,0.396,0.742,0.619
mxfp4    0.438,0.564,0.842,0.634,0.412,0.741,0.636
 
Quant    Perplexity      Peak Memory   Tokens/sec
bf16     9.127 ± 0.095   22.01 GB      1438
mxfp8    8.936 ± 0.091   14.91 GB      1172
q8-hi    9.164 ± 0.096   15.30 GB      1220
q8       9.120 ± 0.095   15.04 GB      1219
qx86-hi  9.246 ± 0.097   14.79 GB      1190
qx64-hi 10.965 ± 0.120   12.92 GB      1211
mxfp4    9.588 ± 0.100   12.81 GB      1219

Thinking mode
bf16     0.513,0.707,0.778,0.656,0.428,0.768,0.635
q8       0.509,0.705,0.779,0.656,0.432,0.768,0.638
Previous modelbrainwaves
gemma-4-E4B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.436,0.528,0.839,0.637,0.416,0.748,0.627
mxfp4    0.432,0.547,0.846,0.626,0.396,0.735,0.627

Quant    Perplexity
mxfp8    8.836 ± 0.091
mxfp4    9.980 ± 0.108
Baseline modelbrainwaves
gemma-4-E4B-it
         arc   arc/e boolq hswag obkqa piqa  wino
mxfp8    0.404,0.489,0.825,0.586,0.392,0.734,0.661
mxfp4    0.414,0.508,0.854,0.562,0.378,0.717,0.645

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8    34.652 ± 0.502  14.80 GB      1146
mxfp4    35.203 ± 0.506  11.06 GB      1200
text
{%- set enable_thinking = true -%}

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.