2x NVIDIA RTX 3090
DesktopTwo RTX 3090s, 48 GB of VRAM in total. A multi-GPU rig is not a single memory pool, so bandwidth and TDP are left empty.
1
Run records
1
Models covered
1
Frameworks covered
L0 Self-reported × 1
Evidence mix
Typical measured performance
Published benchmark averages per model × framework × quantization on this hardware.
- llama.cpp · UD-Q8_K_XL Decode 43.65 · Prefill 1600.18 ·
Fit check
Physics-based estimate from VRAM and memory bandwidth: pick a model to see which quantizations fit and the expected speed
Formula: tok/s = (bandwidth ÷ model size) × 0.55, adapted from llmfit; see run records for measured numbers
Key specs
- Vendor
- NVIDIA
- Architecture
- Ampere
- VRAM
- 48 GB
- Memory bandwidth
- 1800 GB/s
Run records
1 configurations
| Model | Framework | Quantization | Decode | Gen time | Samples |
|---|---|---|---|---|---|
| Qwen3.8-27B | llama.cpp | UD-Q8_K_XL | 43.6 tok/s | — | 1 |