second-state / text-to-image updated 1 year ago

stable-diffusion-3.5-large-GGUF

Name: stable-diffusion-3.5-large-GGUF
Author: second-state

Name Quant method Bits Size Use case ---- ---- ---- ---- ----- clipg-Q80.gguf Q80 8 739 MB clipg.safetensors f16 16 1.39 GB clipl.safetensors f16 16 246 MB sd3.5large-Q40.gguf Q40 4 5.11 GB sd3.5large-Q41.gguf Q41 4 5.61 GB sd3.5large-Q50.gguf Q50 5 6.11 GB sd3.5large-Q51.gguf Q51 5 6.61 GB sd3.5large-Q80.gguf Q80 8 9.11 GB sd3.5large.safetensors f16 16 16.5 GB t5xxl-Q40.gguf Q40 4 2.75 GB t5xxl-Q41.gguf Q41 4 3.06 G...

Params

—

Context

—

Downloads 30d

20 K

Likes

Licence: other Not gated GGUF · SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

21 K19 K

Jul 28Jul 31Aug 3Aug 6

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
sd3.5_large-Q4_0.gguf	Q4_0	5.1 GB	6.1 GB	✅ Runs comfortably
sd3.5_large-Q4_1.gguf	Q4_1	5.6 GB	6.7 GB	✅ Runs comfortably
sd3.5_large-Q5_0.gguf	Q5_0	6.1 GB	7.2 GB	✅ Runs comfortably
sd3.5_large-Q5_1.gguf	Q5_1	6.6 GB	7.8 GB	✅ Runs comfortably
sd3.5_large-Q8_0.gguf	Q8_0	9.1 GB	10.5 GB	✅ Runs comfortably
model.safetensors	fp16	27.9 GB	31.2 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Licence: other
First seen on the Hub: 2024-11-19
Base model: stable-diffusion-3.5-large
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base stable-diffusion-3.5-large stabilityai 70 K

Compare with

stable-diffusion-v1-5 1.6 M stable-diffusion-xl-base-1.0 1.5 M sdxl-turbo 1.1 M Z-Image-Turbo 1.1 M dreamshaper-7 895 K Flux2-Klein-9B-True-V2 792 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB