GraySoft
Download guIDE →
Model Comparison

qwen/qwen2.5-3b-instruct-ggufvsunsloth/z-image-turbo-gguf

Side-by-side comparison of qwen/qwen2.5-3b-instruct-gguf and unsloth/z-image-turbo-gguf: downloads, license, context length, tasks, and benchmarks.

qwen/qwen2.5-3b-instruct-gguf

Qwen · text-generation

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

qwen/qwen2.5-3b-instruct-ggufunsloth/z-image-turbo-gguf
AuthorQwenunsloth
Pipeline Tasktext-generationtext-to-image
Library—ggml
Downloads406,89244,268
Likes103133
LicenseUnknownUnknown
Context Length——
Created2024-09-172025-12-21
Last Modified2024-09-202026-01-08
Tags
ggufchattext-generationenarxiv:2407.10671base_model:Qwen/Qwen2.5-3B-Instructbase_model:quantized:Qwen/Qwen2.5-3B-Instructlicense:otherendpoints_compatibleregion:us
ggmlggufquantizedunslothtext-to-imageenarxiv:2511.22699arxiv:2511.22677arxiv:2511.13649base_model:Tongyi-MAI/Z-Image-Turbo

View full details: qwen/qwen2.5-3b-instruct-gguf · unsloth/z-image-turbo-gguf