Janus-Pro-7B

The parameter count published for a diffusion model describes the denoiser alone. Running it also requires its text encoder and VAE, and the text encoder is often nearly as large as the denoiser — which is why offloading it is the standard first move when you run out of memory.

We publish component sizes here, not throughput. Community-submitted image-generation rates do exist for many GPUs and we show them on the hardware pages, but they aggregate runs at different resolutions, step counts and settings, so they cannot be attributed to one model. Peak memory during sampling is unmeasured by any public source, and we do not estimate it.

A parameters × bits ÷ 8 estimate puts Q4_K_M at roughly 3.88 GiB. The real file is 3.93 GiB, because a quantization is a mixture and some tensors are always kept at higher precision.

How much VRAM does Janus-Pro-7B need?

Q4_K_M is exactly 4,223,359,936 bytes (3.93 GiB) in weights. Add the KV cache, which depends on your context length, plus roughly half a gigabyte of runtime overhead.

How large is Janus-Pro-7B's KV cache?

15.00 GiB at 32K context with an f16 cache, computed per layer. Quantizing the cache to q8_0 roughly halves it, which is often the difference between a context length fitting and not.

Which quantization of Janus-Pro-7B should I use?

Q4_K_M is the usual default. Pick the largest quantization that fits your card at the context you actually need — the table above gives exact sizes for every one published.