ERNIE-Image-Turbo-GGUF
This is a GGUF quantized version of ERNIE-Image-Turbo. unsloth/ERNIE-Image-Turbo-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision. - Uses tooling from ComfyUI-GGUF by city96.
Params
—
Context
—
Downloads 30d
112 K
Likes
231
Download history
daily snapshots · 31 days
▲ 78 K in the last 30 days (232.1%)
153 K54 K
Sep 24Oct 4Oct 14Oct 23
153 K34 K
Sep 23Oct 3Oct 13Oct 23
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| ernie-image-turbo-Q3_K_S.gguf | Q3_K_S | 3.8 GB | 4.7 GB | ✅ Runs comfortably |
| ernie-image-turbo-UD-Q2_K.gguf | Q2_K | 4.0 GB | 4.9 GB | ✅ Runs comfortably |
| ernie-image-turbo-Q4_0.gguf | Q4_0 | 4.8 GB | 5.7 GB | ✅ Runs comfortably |
| ernie-image-turbo-UD-Q3_K_M.gguf | Q3_K_M | 4.8 GB | 5.8 GB | ✅ Runs comfortably |
| ernie-image-turbo-Q4_K_S.gguf | Q4_K_S | 4.9 GB | 5.9 GB | ✅ Runs comfortably |
| ernie-image-turbo-Q4_1.gguf | Q4_1 | 5.3 GB | 6.3 GB | ✅ Runs comfortably |
| ernie-image-turbo-UD-Q4_K_M.gguf | Q4_K_M | 5.8 GB | 6.9 GB | ✅ Runs comfortably |
| ernie-image-turbo-BF16.gguf | GGUF | 16.1 GB | 18.2 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Licence
- apache-2.0
- First seen on the Hub
- 2026-04-14
- Training datasets
- undisclosed
- Added to our catalog
- 2026-09-23
Compare with any text-to-image model
Popular comparisons
Appears in