NVIDIA GeForce RTX 5050
8 GB · 320 GB/s · 130 W
In short
The NVIDIA GeForce RTX 5050 has 8 GB of GDDR6 memory with 320 GB/s of bandwidth, which sets how fast it generates text. At 8k context it runs 38 of the 129 open models we track fully in memory; the most capable is gpt-oss 20B at MXFP4, at about 45 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5050 in the US is $380 at eBay; used, it starts at $380 (asking price).
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| eBayMSI GeForce RTX 5050 Shadow 2X OC 8GB Graphics Card | New | $380 | In stock | 7 min ago | Buy |
| eBayMSI SHADOW GeForce RTX 5050 8GB GDDR6 PCI Express 5.0 Graphics Card RTX 5050 8G | used, asking price | $380 | In stock | 7 min ago | Buy |
| eBayMSI GeForce RTX 5050 8G SHADOW 2X OC NEW | New | $399 | In stock | 7 min ago | Buy |
| eBayNew MSI GeForce RTX 5050 OC 8GB GDDR6 Graphics Card G5050-8S2C Brand New Sealed | New | $399 | In stock | 7 min ago | Buy |
| eBayMSI SHADOW GeForce RTX 5050 8GB GDDR6 PCI Express 5.0 Graphics Card | used, asking price | $399 | In stock | 7 min ago | Buy |
| eBayZOTAC Gaming GeForce RTX 5050 288-1N792-200Z6 | used, asking price | $400 | In stock | 7 min ago | Buy |
| eBayGIGABYTE RTX 5050 8GB vram | used, asking price | $400 | In stock | 7 min ago | Buy |
| eBayASUS Prime GeForce RTX 5050 8GB GDDR6 OC Edition Gaming Graphics Card | used, asking price | $400+ $6 delivery | In stock | 7 min ago | Buy |
| eBayASUS Dual GeForce RTX 5050 8GB GDDR6 OC Edition Graphics Card | New | $410 | In stock | 7 min ago | Buy |
| eBayNEW Zotac GAMING GeForce RTX 5050 Twin Edge OC NVIDIA 8 GB GDDR6 GPU Video Card | New | $425 | In stock | 7 min ago | Buy |
| eBayGIGABYTE RTX 5050 GAMING OC 8GB GDDR6 Triple Fan DLSS 4.5 NEW | New | $425 | In stock | 7 min ago | Buy |
| eBayMSI GeForce RTX 5050 8G SHADOW 2X OC | used, asking price | $430 | In stock | 7 min ago | Buy |
| eBayASUS PRIME GEFORCE RTX 5050 8GB *NEW* SEALED GPU | New | $450+ $6 delivery | In stock | 7 min ago | Buy |
| eBayNEW MSI Geforce RTX 5050 8GB Shadow 2X OC Gaming Graphics Card | New | $520 | In stock | 7 min ago | Buy |
| eBayGIGABYTE GeForce RTX 5050 OC Low Profile 8G Graphics Card | New | $649 | In stock | 7 min ago | Buy |
Price history
Lowest price shown each day over the last 90 days.
What two of them run
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @8k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.6 GB | 82k128k with q8 cache | 45tok/sest. | 643 tok/s | chat, coding, agents |
| Gemma 4 12B | Q8_0 | fits | 13.4 GB | 73k122k with q8 cache | 15tok/sest. | 236 tok/s | chat |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 128k212k with q8 cache | 20tok/sest. | 299 tok/s | chat |
| Ministral 3 14B Mistral AI | Q6_K | fits | 12.7 GB | 20k37k with q8 cache | 16tok/sest. | 194 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q6_K | fits | 13.7 GB | 14k27k with q8 cache | 15tok/sest. | 180 tok/s | – |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.4 GB | 38k69k with q8 cache | 20tok/sest. | 315 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.4 GB | 38k40k with q8 cache | 20tok/sest. | 315 tok/s | chat |
| Phi-4 14B Microsoft | Q6_K | fits | 13.9 GB | 12k16k with q8 cache | 15tok/sest. | 181 tok/s | – |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.6 GB | 255k256k with q8 cache | 41tok/sest. | 601 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.6 GB | 38k69k with q8 cache | 20tok/sest. | 295 tok/s | chat |
| Granite 4.2 8B IBM | Q8_0 | fits | 11.1 GB | 30k56k with q8 cache | 19tok/sest. | 292 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 9.0 GB | 128k | 23tok/sest. | 362 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.9 GB | 100k125k with q8 cache | 81tok/sest. | 2112 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 8.3 GB | 57k104k with q8 cache | 26tok/sest. | 326 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.7 GB | 32k | 314tok/sest. | 4421 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.0 GB | 256k | 213tok/sest. | 3042 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.6 GB | 256k | 128tok/sest. | 1248 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 3.0 GB | 256k | 101tok/sest. | 1603 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.1 GB | 128k | 93tok/sest. | 1392 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.0 GB | 128k | 65tok/sest. | 920 tok/s | chat, coding, agents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 4.3 GB | 128k | 59tok/sest. | 926 tok/s | chat, coding, agents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 4.3 GB | 32k | 59tok/sest. | 817 tok/s | chat, coding, agents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 4.3 GB | 263k441k with q8 cache | 58tok/sest. | 655 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | fits | 11.2 GB | 109k128k with q8 cache | 55tok/sest. | 858 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q8_0 | fits | 5.1 GB | 122k128k with q8 cache | 46tok/sest. | 613 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 5.4 GB | 95k172k with q8 cache | 44tok/sest. | 628 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 5.4 GB | 119k128k with q8 cache | 44tok/sest. | 659 tok/s | chat, coding |
| Kimi VL A3B Moonshot AI | mlx-6bit | fits | 14.3 GB | 23k37k with q8 cache | 43tok/sest. | 805 tok/s | chat, coding, agents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.3 GB | 83k125k with q8 cache | 42tok/sest. | 1018 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 5.7 GB | 251k256k with q8 cache | 40tok/sest. | 601 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 9.1 GB | 101k128k with q8 cache | 23tok/sest. | 351 tok/s | chat |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 9.1 GB | 32k | 23tok/sest. | 276 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 10.1 GB | 43k79k with q8 cache | 21tok/sest. | 326 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.6 GB | 38k69k with q8 cache | 20tok/sest. | 295 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.8 GB | 97k128k with q8 cache | 19tok/sest. | 255 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.4 GB | 60k64k with q8 cache | 16tok/sest. | 255 tok/s | chat |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q6_K | fits | 12.7 GB | 20k37k with q8 cache | 16tok/sest. | 194 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q6_K | fits | 13.9 GB | 12k22k with q8 cache | 14tok/sest. | 177 tok/s | – |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 17.1 GB | – | 8tok/sest. | 95 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.4 GB | – | 12tok/sest. | 167 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 17.4 GB | – | 8tok/sest. | 94 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 19.6 GB | – | 6tok/sest. | 76 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.8 GB | – | 17tok/sest. | 221 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 21.6 GB | – | 31tok/sest. | 712 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 17.4 GB | – | 8tok/sest. | 94 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 16.9 GB | – | 30tok/sest. | 623 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 21.9 GB | – | 30tok/sest. | 707 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 18.6 GB | – | 22tok/sest. | 432 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 15.7 GB | 2k3k with q8 cache | 11tok/sest. | 112 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 22.9 GB | – | 26tok/sest. | 720 tok/s | chat, coding, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 19.2 GB | – | 27tok/sest. | 549 tok/s | chat |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.2 GB | – | 26tok/sest. | 584 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 21.6 GB | – | 5tok/sest. | 64 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 15.7 GB | 2k3k with q8 cache | 11tok/sest. | 112 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 17.6 GB | – | 8tok/sest. | 94 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 21.6 GB | – | 5tok/sest. | 67 tok/s | – |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 16.1 GB | – | 50tok/sest. | 1053 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 15.7 GB | 2k3k with q8 cache | 11tok/sest. | 114 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 15.7 GB | 2k3k with q8 cache | 11tok/sest. | 114 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 15.7 GB | 2k3k with q8 cache | 11tok/sest. | 114 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 15.7 GB | 2k3k with q8 cache | 11tok/sest. | 112 tok/s | – |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 17.4 GB | – | 8tok/sest. | 87 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 19.9 GB | – | 6tok/sest. | 79 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 21.0 GB | – | 5tok/sest. | 84 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 92.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.6 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.9 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 73.2 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.3 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 46.6 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 59.9 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 44.8 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 46.6 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 43.2 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.8 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 43.2 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 378.3 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 379.2 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.5 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 156.2 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 73.7 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 205.6 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 61.8 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 204.8 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 68.2 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.6 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 384.2 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.8 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.7 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 748.2 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 63.6 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.8 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 580.3 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.9 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.9 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 118.4 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 241.8 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 73.7 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- GeForce RTX 5050
- Memory
- 8 GB GDDR6
- Memory bus
- 128-bit
- Memory bandwidth
- 320 GB/s
- FP16 compute
- 13.169 TFLOPS
- Software
- CUDA
- Board power
- 130 W
- PCIe generation
- Gen 5
- PCIe lanes
- x8
Compare with
Questions
- How much memory does the NVIDIA GeForce RTX 5050 have for AI models?
- The NVIDIA GeForce RTX 5050 has 8 GB of GDDR6 memory with 320 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the NVIDIA GeForce RTX 5050 can run locally?
- gpt-oss 20B (MXFP4) fits fully in its memory at 8k context and generates at about 45 tok/s, an estimate from its memory bandwidth. 38 of the 129 models we track fit at that context.
- Can the NVIDIA GeForce RTX 5050 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 92 GB at 8k context, more than the NVIDIA GeForce RTX 5050 and system RAM can hold.
- How much does the NVIDIA GeForce RTX 5050 cost in the US?
- The best new price for the NVIDIA GeForce RTX 5050 in the US is $380 at eBay; used, it starts at $380 (asking price).
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.