Image models · Bria AI
Fibo 2.0 Dev
- Backbone
- 8.1B
- Native output
- 1024×1024
- Default steps
- 50
- License
- bria-fibo
- Released
- 2026-10
How to run it
Original weights · Hugging Face
Full-precision files from Bria AI, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.
Apps that run Fibo 2.0 Dev
Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.
| App | Type | Opens it as | Systems | Engine | Start |
|---|---|---|---|---|---|
| ComfyUI | Desktop app | Built-in support | macOSWindowsLinux | Get ComfyUI | |
 SwarmUI |
Desktop app | Built-in support | macOSWindowsLinux | Get SwarmUI | |
| SD.Next | Desktop app | Built-in support | macOSWindowsLinux | Get SD.Next | |
 Stability Matrix |
Desktop app | Built-in support | macOSWindowsLinux | Get Stability Matrix |
Memory needed
Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.
| Precision | Everything on GPU | Text encoder offloaded | Sequential offload | Download |
|---|---|---|---|---|
FP16 | 27.7 GB | 18.9 GB | 8.1 GB | Original weights (opens in a new tab) |
Components
- Backbone: 8.13B
- VAE: 0.084B
- Qwen3-VL 4B: 4.44B
Best hardware for Fibo 2.0 Dev
The least expensive GPU in our catalog that runs it without offloading is the Intel Arc B570 (launch price $219) at FP16.
| Quality | Hardware | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA GeForce RTX 5090 |
FP16 | 27.7 GB / 32.0 GB | 19 s | Runs welltight fit |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA GeForce RTX 4090 |
FP16 | 18.9 GB / 24.0 GB | 24 s | Runs wellencoder in RAM |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. |  AMD Radeon RX 7900 XTX |
FP16 | 18.9 GB / 24.0 GB | 26 s | Runs wellencoder in RAM |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA RTX PRO 6000 Blackwell |
FP16 | 27.7 GB / 96.0 GB | 16 s | Runs well |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. |  AMD Radeon RX 9070 XT |
FP16 | 8.1 GB / 16.0 GB | 39 s | Runs wellCPU offload |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA GeForce RTX 5080 |
FP16 | 8.1 GB / 16.0 GB | 39 s | Runs wellCPU offload |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA A100 40GB |
FP16 | 27.7 GB / 40.0 GB | 23 s | Runs well |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA L40S |
FP16 | 27.7 GB / 48.0 GB | 21 s | Runs well |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA RTX 6000 Ada Generation |
FP16 | 27.7 GB / 48.0 GB | 21 s | Runs well |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. |  NVIDIA L40 |
FP16 | 27.7 GB / 48.0 GB | 21 s | Runs well |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.