unsloth/qwen3-30b-a3b-ggufvsunsloth/z-image-turbo-gguf
Side-by-side comparison of unsloth/qwen3-30b-a3b-gguf and unsloth/z-image-turbo-gguf: downloads, license, context length, tasks, and benchmarks.
unsloth/qwen3-30b-a3b-gguf
If you are using llama.cpp, Ollama, Open WebUI etc., you can add /think and /no_think to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations. Here is an example of mu…
unsloth/z-image-turbo-gguf
# 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
| unsloth/qwen3-30b-a3b-gguf | unsloth/z-image-turbo-gguf | |
|---|---|---|
| Author | unsloth | unsloth |
| Pipeline Task | text-generation | text-to-image |
| Library | transformers | ggml |
| Downloads | 33,648 | 44,268 |
| Likes | 274 | 133 |
| License | Unknown | Unknown |
| Context Length | — | — |
| Created | 2025-04-28 | 2025-12-21 |
| Last Modified | 2025-06-08 | 2026-01-08 |
| Tags |
View full details: unsloth/qwen3-30b-a3b-gguf · unsloth/z-image-turbo-gguf