NVIDIA RTX 5000 Ada Generation for local LLMs
Written by Jakub Rusinowski · Last updated
With 32 GB of GDDR6 at 576 GB/s, the RTX 5000 Ada Generation runs 110 catalogued models at Q4_K_M with 8K context. The largest that fits is Gemma 3 27B Instruct (~25.4 GB), and the top pick is Qwen 3.6 35B-A3B at 75–144 tok/s.
32 GB of GDDR6 with ECC, 576 GB/s, 250 W.
Models that run on the RTX 5000 Ada Generation
Q4_K_M, 8K context, 32 GB usable. Ranked by quality and speed.
| Model | Memory · marker = 32 GB | VRAM | Speed |
|---|---|---|---|
| Qwen 3.6 35B-A3B Qwen 3.6 | 21.9 GB | 75–144 tok/s | |
| Nex-N2.5 mini Nex-N2.5 | 21.9 GB | 75–144 tok/s | |
| Nex-N2 mini Nex-N2 | 21.9 GB | 75–144 tok/s | |
| Qwen 3.5 35B-A3B Qwen 3.5 | 21.9 GB | 75–144 tok/s | |
| Laguna XS 2.1 33B-A3B Poolside Laguna XS 2.1 | 20.7 GB | 75–145 tok/s | |
| Qwen 3 32B Qwen 3 | 22.8 GB | 16–30 tok/s | |
| Aya Expanse 32B Aya Expanse | 21.6 GB | 17–32 tok/s | |
| EXAONE 3.5 32B EXAONE 3.5 | 22.3 GB | 16–31 tok/s | |
| Cogito v1 32B Cogito v1 | 22.3 GB | 16–31 tok/s | |
| Granite 4.0 Small-H 32B-A9B IBM Granite 4.0 | 20.1 GB | 43–83 tok/s | |
| Olmo 3 32B Olmo 3 | 20.1 GB | 16–31 tok/s | |
| DeepSeek R1 Distill Qwen 32B DeepSeek R1 | 22.3 GB | 16–31 tok/s |
Buy it or rent the same memory
Buy the card, or rent a GPU with the same memory by the hour to try models first.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
Speed vs other GPUs
Llama 3.1 8B, Q4_K_M. Estimated ranges. How this is calculated
Specifications
Specs last updated 2026-10-07.
- Memory
- 32 GB GDDR6
- Memory bandwidth
- 576 GB/s
- Memory bus
- 256-bit
- Architecture
- Ada Lovelace AD102
- Series
- RTX Ada Generation
- Board power
- 250 W
- Release year
- 2023
- Compute backends
- CUDA, VULKAN
- Usable for models
- 32 GB
Similar GPUs
Frequently asked questions
Can the NVIDIA RTX 5000 Ada Generation run local LLMs?
Yes. With 32 GB (32 GB usable by a model) it runs 110 of the catalogued models at Q4_K_M with 8K context; the largest is Gemma 3 27B Instruct, needing about 25.4 GB.
How fast is the NVIDIA RTX 5000 Ada Generation for AI inference?
It is estimated to run Llama 3.1 8B at 56–107 tok/s at Q4_K_M. Llama 3.3 70B does not fit: it needs about 44 GB against 32 GB usable. These are modelled estimates from memory bandwidth, not measurements; the methodology page shows the formula.
What LLMs can I run on 32 GB?
Among the best that fit: Qwen 3.6 35B-A3B, Nex-N2.5 mini, Nex-N2 mini, Qwen 3.5 35B-A3B, Laguna XS 2.1 33B-A3B.