Can you run FLUX.1 dev locally?

FLUX.1 family · August 2024 · 12.00B parameters · Hugging Face model card

How much VRAM does FLUX.1 dev need at each quantization?

FLUX.1 dev needs 9.9 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.

Diffusion transformer — no KV cache. Table adds a 2 GB activation overhead for 1024×1024 generation (latent buffers, VAE, text encoders partially offloadable).

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: 12B-parameter rectified-flow transformer — HF model card (black-forest-labs/FLUX.1-dev). VRAM figures calculated (weights + 10% + 2 GB activation overhead); community-standard FP8/NF4/GGUF variants assumed per checkpoint format.

Which GPUs can run FLUX.1 dev locally?

At Q4_K_M with a 4k context, FLUX.1 dev needs 9.9 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 FLUX.1 dev comfortably (25%+ VRAM headroom)

Minimum GPUs that fit FLUX.1 dev at Q4_K_M

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

Needs 2+ GPUs to run FLUX.1 dev

One of these cards is too small on its own, but a pair (tensor or pipeline parallel, ~90% efficiency) covers the 9.9 GB requirement. See our multi-GPU guide for setup.

Can a Mac run FLUX.1 dev?

Yes — these Apple Silicon machines fit FLUX.1 dev 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 FLUX.1 dev run on mini PCs, Jetson, or NPU devices?

These edge and NPU devices from our database have enough memory for FLUX.1 dev 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 FLUX.1 dev?

These mini PCs and workstations from our database fit FLUX.1 dev 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 FLUX.1
• Best GPU for Stable Diffusion
• Best Laptops for Stable Diffusion