GraySoft
Download guIDE →
Model Comparison

andycurrent/gemma-3-1b-it-glm-4.7-flash-heretic-uncensored-thinking_ggufvsdphn/dolphin3.0-llama3.1-8b-gguf

Side-by-side comparison of andycurrent/gemma-3-1b-it-glm-4.7-flash-heretic-uncensored-thinking_gguf and dphn/dolphin3.0-llama3.1-8b-gguf: downloads, license, context length, tasks, and benchmarks.

andycurrent/gemma-3-1b-it-glm-4.7-flash-heretic-uncensored-thinking_gguf

Andycurrent · text-generation

This repository hosts Gemma 3 – 1B IT GLM-4.7 Flash Heretic Uncensored Thinking, a lightweight 1 billion–parameter instruction-tuned model derived from Google’s Gemma 3 1B IT base. This variant is optimized for fast inference, structured reasoning behavior, and minimal refusal p…

dphn/dolphin3.0-llama3.1-8b-gguf

dphn · —

Part of the Dolphin 3.0 Collection Curated and trained by Eric Hartford, Ben Gitter, BlouseJury and Cognitive Computations ![Discord](https://discord.gg/cognitivecomputations) Discord: https://discord.gg/cognitivecomputations

Side-by-side Specifications

andycurrent/gemma-3-1b-it-glm-4.7-flash-heretic-uncensored-thinking_ggufdphn/dolphin3.0-llama3.1-8b-gguf
AuthorAndycurrentdphn
Pipeline Tasktext-generation—
Library——
Downloads134,37441,898
Likes15162
LicenseUnknownUnknown
Context Length——
Created2026-02-182025-01-02
Last Modified2026-02-182025-01-05
Tags
ggufuncensoredtext-generationreasoninginstruction-tunedlightweightenbase_model:google/gemma-3-1b-itbase_model:quantized:google/gemma-3-1b-itlicense:gemma
ggufendataset:OpenCoder-LLM/opc-sft-stage1dataset:OpenCoder-LLM/opc-sft-stage2dataset:microsoft/orca-agentinstruct-1M-v1dataset:microsoft/orca-math-word-problems-200kdataset:NousResearch/hermes-function-calling-v1dataset:AI-MO/NuminaMath-CoTdataset:AI-MO/NuminaMath-TIRdataset:allenai/tulu-3-sft-mixture

View full details: andycurrent/gemma-3-1b-it-glm-4.7-flash-heretic-uncensored-thinking_gguf · dphn/dolphin3.0-llama3.1-8b-gguf