supergemma4 26b uncensored mlx 4bit v2

gemma

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released April 2026context N/A

A text-focused model built on Google's Gemma architecture, published by Jiunsong with an 'uncensored' configuration that removes typical content filtering guardrails. This means it responds more freely to a wider range of prompts, but also without the safety constraints that are standard in most deployments. The 4-bit quantization keeps memory requirements low at the cost of some precision.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Creative Writing

Strong

Factual Knowledge

Moderate

Multilingual

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

supergemma4 26b uncensored mlx 4bit v2

gemma

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released April 2026context N/A

A text-focused model built on Google's Gemma architecture, published by Jiunsong with an 'uncensored' configuration that removes typical content filtering guardrails. This means it responds more freely to a wider range of prompts, but also without the safety constraints that are standard in most deployments. The 4-bit quantization keeps memory requirements low at the cost of some precision.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Creative Writing

Strong

Factual Knowledge

Moderate

Multilingual

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Glossary

4-bit QuantizationA specific type of quantization that represents model weights using only 4 bits instead of the original 32 bits, enabling very efficient inference on consumer hardware.ArchitectureThe underlying structural design of a neural network that defines how data flows through layers and components.Content FilteringSafety mechanisms built into a model that prevent it from generating harmful, inappropriate, or restricted content.GuardrailsSafety mechanisms built into a model to refuse harmful requests or prevent it from generating unsafe content.PrecisionThe level of numerical detail a model uses to represent its internal values; higher precision means more accurate calculations but requires more memory.QuantizationReducing a model's numerical precision (e.g., from 16-bit to 4-bit) to shrink memory usage and speed up inference.Safety ConstraintsRules or limits that ensure a learning system operates within acceptable bounds and avoids harmful actions.Text-Focused ModelA model designed specifically to process and generate text, without support for images, audio, or other data types.Text-Focused ModelA language model designed to work exclusively with text input and output, without support for images, audio, or other modalities.UncensoredA model without built-in safety filters or content restrictions, allowing it to generate responses on any topic without refusal.