Model Comparison

abiray/gemma-4-e4b-it-heretic-ggufvsdat-lequoc/fast-apply-1.5b-v1.0_gguf

Side-by-side comparison of abiray/gemma-4-e4b-it-heretic-gguf and dat-lequoc/fast-apply-1.5b-v1.0_gguf: downloads, license, context length, tasks, and benchmarks.

abiray/gemma-4-e4b-it-heretic-gguf

Abiray · any-to-any

This repository contains GGUF format quantizations of coder3101/gemma-4-E4B-it-heretic.

dat-lequoc/fast-apply-1.5b-v1.0_gguf

dat-lequoc · —

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Side-by-side Specifications

	abiray/gemma-4-e4b-it-heretic-gguf	dat-lequoc/fast-apply-1.5b-v1.0_gguf
Author	Abiray	dat-lequoc
Pipeline Task	any-to-any	—
Library	—	transformers
Downloads	26,785	34,562
Likes	28	3
License	Unknown	Unknown
Context Length	—	—
Created	2026-04-03	2024-10-24
Last Modified	2026-04-04	2024-10-24
Tags	ggufllama-cppgemma-4any-to-anybase_model:coder3101/gemma-4-E4B-it-hereticbase_model:quantized:coder3101/gemma-4-E4B-it-hereticlicense:apache-2.0endpoints_compatibleregion:usimatrix	transformersggufqwen2text-generation-inferenceunslothenbase_model:unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bitbase_model:quantized:unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bitlicense:apache-2.0endpoints_compatible

View full details: abiray/gemma-4-e4b-it-heretic-gguf · dat-lequoc/fast-apply-1.5b-v1.0_gguf