NVIDIA GeForce RTX 5050 for local LLMs
Written by Jakub Rusinowski · Last updated
With 8 GB of GDDR6 at 320 GB/s, the RTX 5050 runs 61 catalogued models at Q4_K_M with 8K context. The largest that fits is K2 Horizon 7B (~7.4 GB), and the top pick is Qwen 3.5 9B at 28–58 tok/s.
The cheapest Blackwell desktop card: 8 GB of GDDR6 (not GDDR7) on a 128-bit bus, 320 GB/s. Enough for 7-8B models at Q4 with a short context.
Models that run on the RTX 5050
Q4_K_M, 8K context, 8 GB usable. Ranked by quality and speed.
| Model | Memory · marker = 8 GB | VRAM | Speed |
|---|---|---|---|
| Qwen 3.5 9B Qwen 3.5 | 6.6 GB | 28–58 tok/s | |
| GLM-4 9B GLM-4.7 / GLM-Z1 | 6.2 GB | 24–51 tok/s | |
| GLM-4.6V-Flash 9B GLM-4.6V | 6.2 GB | 24–51 tok/s | |
| EuroLLM 9B EuroLLM | 6.2 GB | 24–51 tok/s | |
| MiMo-V2.6 Distill 9B MiMo-V2.6 | 6.5 GB | 28–58 tok/s | |
| Ternary Bonsai 2 9B Ternary Bonsai 2 | 6.5 GB | 28–58 tok/s | |
| InternLM 3 8B Instruct InternLM 3 | 6.5 GB | 28–58 tok/s | |
| LFM2.5-8B-A1B LFM2.5 | 5.8 GB | 66–136 tok/s | |
| Qwen 3 8B Qwen 3 | 7 GB | 26–54 tok/s | |
| Aya Expanse 8B Aya Expanse | 6.7 GB | 27–56 tok/s | |
| Ministral 8B Ministral | 6.9 GB | 27–55 tok/s | |
| Gemma 4 E4B Gemma 4 | 5.6 GB | 27–56 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.
or compare on Vast.ai from $0.35/hr (typical low · varies)
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
- 8 GB GDDR6
- Memory bandwidth
- 320 GB/s
- Memory bus
- 128-bit
- Architecture
- Blackwell GB207
- Series
- RTX 50-series
- Board power
- 130 W
- Release year
- 2025
- Launch price
- $249
- Compute backends
- CUDA, VULKAN
- Usable for models
- 8 GB
Similar GPUs
Frequently asked questions
Can the NVIDIA GeForce RTX 5050 run local LLMs?
Yes. With 8 GB (8 GB usable by a model) it runs 61 of the catalogued models at Q4_K_M with 8K context; the largest is K2 Horizon 7B, needing about 7.4 GB.
How fast is the NVIDIA GeForce RTX 5050 for AI inference?
It is estimated to run Llama 3.1 8B at 30–61 tok/s at Q4_K_M. Llama 3.3 70B does not fit: it needs about 44 GB against 8 GB usable. These are modelled estimates from memory bandwidth, not measurements; the methodology page shows the formula.
What LLMs can I run on 8 GB?
Among the best that fit: Qwen 3.5 9B, GLM-4 9B, GLM-4.6V-Flash 9B, EuroLLM 9B, MiMo-V2.6 Distill 9B.