GraySoft
Download guIDE →
Model Comparison

ggml-org/gemma-4-e4b-it-ggufvsjayn7/z-image-turbo-gguf

Side-by-side comparison of ggml-org/gemma-4-e4b-it-gguf and jayn7/z-image-turbo-gguf: downloads, license, context length, tasks, and benchmarks.

ggml-org/gemma-4-e4b-it-gguf

ggml-org · —

# gemma-4-E4B-it-GGUF Recommended way to run this model: ``sh llama-server -hf ggml-org/gemma-4-E4B-it-GGUF `` Then, access http://localhost:8080

jayn7/z-image-turbo-gguf

jayn7 · text-to-image

# Diffusers uses SDPA by default. Switch to Custom attention backend for better efficiency if supported: #pipeline.transformer.set_attention_backend("_sage_qk_int8_pv_fp16_triton") # Enable Sage Attention #pipeline.transformer.set_attention_backend("flash") # Enable Flash-Attent…

Side-by-side Specifications

ggml-org/gemma-4-e4b-it-ggufjayn7/z-image-turbo-gguf
Authorggml-orgjayn7
Pipeline Task—text-to-image
Library——
Downloads129,29241,377
Likes42348
LicenseUnknownUnknown
Context Length——
Created2026-04-012025-11-27
Last Modified2026-04-122025-12-05
Tags
ggufbase_model:google/gemma-4-E4B-itbase_model:quantized:google/gemma-4-E4B-itendpoints_compatibleregion:usconversational
gguftext-to-imageimage-generationbase_model:Tongyi-MAI/Z-Image-Turbobase_model:quantized:Tongyi-MAI/Z-Image-Turbolicense:apache-2.0region:us

View full details: ggml-org/gemma-4-e4b-it-gguf · jayn7/z-image-turbo-gguf