// Stable Diffusion / Stable Audio · Text LLM
sv4d2.0: VRAM & local deployment
Text LLM model published by Stability AI.
released 2025-02-20licence: Commercial with conditionsmemory figures are estimates
01Specs
| Publisher | Stability AI · stabilityai |
|---|---|
| Family / series | Stable Diffusion / Stable Audio · sv4d2.0 |
| Type | Text LLM |
| Parameters | not stated in official metadata |
| Context length | — |
| Licence | stabilityai-ai-community · Commercial with conditionsCommercial use allowed under the publisher’s own licence terms (user caps, acceptable-use policy, attribution or region limits). Read it before shipping. |
| Released | 2025-02-20 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
No estimate: the official metadata does not give a parameter count. Check the model card for tested hardware.
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- Diffusers — mentioned in the official model card
04Official repositories & quantised builds
1 official repo(s) from stabilityai.
- sv4d2.0 main
05Other Stable Diffusion / Stable Audio models
All 10 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| stable-audio-3-medium | 2.31B | 2.0 GB | 2026-05-17 |
| stable-audio-3-small-music | 568M | 0.9 GB | 2026-05-17 |
| stable-audio-3-small-sfx | 568M | 0.9 GB | 2026-05-17 |
| stable-audio-open-small | 497M | 0.8 GB | 2025-05-12 |
| stable-diffusion-3.5-medium | 2.47B | 2.1 GB | 2024-10-29 |
| stable-diffusion-3.5-large | 8.15B | 5.9 GB | 2024-10-22 |
| stable-diffusion-3.5-large-turbo | 8.15B | 5.9 GB | 2024-10-22 |
| stable-diffusion-3-medium-diffusers | 2.08B | 1.9 GB | 2024-06-12 |
06Sources
Data checked 2025-04-04. Parameters, context and licence are copied from the official repository; memory figures are our estimates.