Can you run Stable Diffusion 3.5 Large locally?

Stable Diffusion 3.5 family · October 2024 · 8.00B parameters · Hugging Face model card

How much VRAM does Stable Diffusion 3.5 Large need at each quantization?

Stable Diffusion 3.5 Large needs 7.3 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level including runtime overhead.

MMDiT-X diffusion transformer — no KV cache. Table adds a 2 GB activation overhead; the T5-XXL text encoder (4.7B params, ~9.4 GB FP16) can be offloaded to CPU RAM or swapped for smaller encoders.

Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (not applicable to this architecture). Source: 8B-parameter MMDiT model; SD 3.5 Medium is 2.5B — Stability AI / HF model card (stabilityai/stable-diffusion-3.5-large).

Which GPUs can run Stable Diffusion 3.5 Large locally?

At Q4_K_M with a 4k context, Stable Diffusion 3.5 Large needs 7.3 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.

Runs Stable Diffusion 3.5 Large comfortably (25%+ VRAM headroom)

Minimum GPUs that fit Stable Diffusion 3.5 Large at Q4_K_M

These GPUs hold the model but leave little headroom — keep contexts short.

Can a Mac run Stable Diffusion 3.5 Large?

Yes — these Apple Silicon machines fit Stable Diffusion 3.5 Large at Q4_K_M, since macOS lets the GPU use about 75% of unified memory. Generation speed is bound by memory bandwidth, so the GB/s column matters as much as capacity.

Can Stable Diffusion 3.5 Large run on mini PCs, Jetson, or NPU devices?

These edge and NPU devices from our database have enough memory for Stable Diffusion 3.5 Large at Q4_K_M. Their memory bandwidth is far below discrete GPUs, so expect a fraction of desktop generation speed.

Which pre-built systems can run Stable Diffusion 3.5 Large?

These mini PCs and workstations from our database fit Stable Diffusion 3.5 Large at Q4_K_M. Usable-memory figures are conservative: Windows shares about half of system RAM with the GPU by default (Linux can expose more), macOS lets Apple Silicon GPUs use about 75% of unified memory, and Linux unified-memory systems such as GB10 expose roughly 90%. Generation speed is bound by memory bandwidth, so compare the GB/s column before buying.

Frequently asked questions

Related guides

• Best GPU for Stable Diffusion
• Best GPU for FLUX.1
• Best Laptops for Stable Diffusion