GraySoft
Model Comparison

mudler/gemma-4-26b-a4b-it-heretic-apex-ggufvsunsloth/z-image-turbo-gguf

Side-by-side comparison of mudler/gemma-4-26b-a4b-it-heretic-apex-gguf and unsloth/z-image-turbo-gguf: downloads, license, context length, tasks, and benchmarks.

mudler/gemma-4-26b-a4b-it-heretic-apex-gguf

mudler · —

**APEX (Adaptive Precision for EXpert Models)** quantizations of gemma-4-26B-A4B-it-heretic — an **abliterated (uncensored)** version of Gemma 4, created with the Heretic tool (v1.2.0) using Arbitrary-Rank Ablation (ARA) on layers 10-30 to reduce refusals while preserving capabi…

unsloth/z-image-turbo-gguf

unsloth · text-to-image

# Use bfloat16 for optimal performance on supported GPUs pipe = ZImagePipeline.from_pretrained( "Tongyi-MAI/Z-Image-Turbo", torch_dtype=torch.bfloat16, low_cpu_mem_usage=False, ) pipe.to("cuda") # [Optional] Attention Backend # Diffusers uses SDPA by default. Switch to Flash Att…

Side-by-side Specifications

mudler/gemma-4-26b-a4b-it-heretic-apex-ggufunsloth/z-image-turbo-gguf
Authormudlerunsloth
Pipeline Tasktext-to-image
Libraryggml
Downloads18,84944,268
Likes22133
LicenseUnknownUnknown
Context Length
Created2026-04-052025-12-21
Last Modified2026-04-052026-01-08
Tags
ggufquantizedapexmoemixture-of-expertsgemma4vlmvisionbase_model:coder3101/gemma-4-26B-A4B-it-hereticbase_model:quantized:coder3101/gemma-4-26B-A4B-it-heretic
ggmlggufquantizedunslothtext-to-imageenarxiv:2511.22699arxiv:2511.22677arxiv:2511.13649base_model:Tongyi-MAI/Z-Image-Turbo

View full details: mudler/gemma-4-26b-a4b-it-heretic-apex-gguf · unsloth/z-image-turbo-gguf