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 32k context it runs 36 of the 129 open models we track fully in memory; the most capable is gpt-oss 20B at MXFP4, at about 37 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5050 in Canada is $570 at Amazon.
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in Canada, cheapest first. Buy links may earn us a commission.
| Retailer | Condition | Price | Stock | Checked | Buy |
|---|---|---|---|---|---|
| AmazonASUS Dual GeForce RTX 5050 8GB GDDR6 Gaming Gaming Graphics Card | New | $570 | In stock | 4 h ago | Buy |
| AmazonASUS Dual GeForce RTX 5050 8GB GDDR6 OC Edition Gaming Graphics Card | New | $590 | In stock | 4 h ago | Buy |
| AmazonMSI Gaming RTX 5050 8G Shadow 2X OC Graphics Card | New | $595 | In stock | 4 h ago | Buy |
| AmazonGIGABYTE NVIDIA Geforce RTX5050 GDDR6 Graphic Board 8 GB GB-N5050 Gaming OC-8GD | New | $600 | In stock | 4 h ago | Buy |
| AmazonMSI Gaming RTX 5050 8G Ventus 2X OC Graphics Card | New | $600 | In stock | 4 h ago | Buy |
| AmazonGigabyte GeForce RTX 5050 Gaming OC 8G Graphics Card | New | $600 | In stock | 4 h ago | Buy |
| AmazonASUS PRIME GeForce RTX 5050 8GB GDDR6 OC Edition Gaming Graphics Card | New | $620 | In stock | 4 h ago | Buy |
| AmazonMSI GeForce RTX 5050 8G Ventus 2X OC Graphics Card | New | $884 | In stock | 4 h ago | Buy |
| AmazonGigabyte GeForce RTX 5050 WINDFORCE OC 8G Graphics Card | New | $1,054 | In stock | 4 h ago | Buy |
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 @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.3 GB | 82k128k with q8 cache | 37tok/sest. | 509 tok/s | chat, coding, agents |
| Gemma 4 12B | Q8_0 | fits | 13.9 GB | 73k122k with q8 cache | 15tok/sest. | 222 tok/s | chat |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 11.2 GB | 128k212k with q8 cache | 19tok/sest. | 276 tok/s | chat |
| Ministral 3 14B Mistral AI | Q4_K_M | fits | 14.0 GB | 37k67k with q8 cache | 15tok/sest. | 153 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q4_K_M | fits | 14.7 GB | 32k40k with q8 cache | 14tok/sest. | 138 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.9 GB | 38k69k with q8 cache | 15tok/sest. | 228 tok/s | chat |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.9 GB | 38k40k with q8 cache | 15tok/sest. | 228 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.5 GB | 255k256k with q8 cache | 35tok/sest. | 517 tok/s | chat, coding, long documents |
| Granite 4.2 8B IBM | Q6_K | fits | 13.3 GB | 41k75k with q8 cache | 15tok/sest. | 209 tok/s | chat |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.9 GB | 38k69k with q8 cache | 15tok/sest. | 220 tok/s | chat |
| Gemma 4 E4B | Q8_0 | fits | 9.8 GB | 128k | 22tok/sest. | 347 tok/s | chat, coding |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 11.2 GB | 100k125k with q8 cache | 45tok/sest. | 1135 tok/s | chat, coding |
| Llama 3.1 8B Meta | Q6_K | fits | 11.4 GB | 57k104k with q8 cache | 18tok/sest. | 240 tok/s | chat |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.2 GB | 32k | 213tok/sest. | 2472 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.4 GB | 256k | 161tok/sest. | 2322 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.0 GB | 256k | 107tok/sest. | 1107 tok/s | chat, coding, agents, long documents |
| LFM3 1.7B Liquid AI | Q8_0 | fits | 3.4 GB | 256k | 88tok/sest. | 1378 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.9 GB | 128k | 70tok/sest. | 930 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 5.1 GB | 128k | 49tok/sest. | 555 tok/s | chat, coding, agents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 5.3 GB | 263k441k with q8 cache | 46tok/sest. | 545 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.8 GB | 128k | 41tok/sest. | 629 tok/s | chat, coding, agents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.8 GB | 32k | 41tok/sest. | 577 tok/s | chat, coding, agents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q4_K_M | fits | 12.1 GB | 109k128k with q8 cache | 40tok/sest. | 616 tok/s | chat, coding |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.8 GB | 83k125k with q8 cache | 38tok/sest. | 820 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Moonshot AI | mlx-5bit | fits | 13.3 GB | 75k123k with q8 cache | 37tok/sest. | 518 tok/s | chat, coding, agents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 6.6 GB | 251k256k with q8 cache | 35tok/sest. | 517 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 7.2 GB | 122k128k with q8 cache | 32tok/sest. | 403 tok/s | chat, coding |
| granite 4.2 3b IBM | Q8_0 | fits | 7.4 GB | 119k128k with q8 cache | 30tok/sest. | 422 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 7.9 GB | 95k172k with q8 cache | 28tok/sest. | 404 tok/s | chat, coding |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 10.2 GB | 32k | 21tok/sest. | 201 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.6 GB | 101k128k with q8 cache | 20tok/sest. | 272 tok/s | chat |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 11.9 GB | 97k128k with q8 cache | 18tok/sest. | 189 tok/s | chat |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 13.2 GB | 43k79k with q8 cache | 16tok/sest. | 240 tok/s | chat |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 13.5 GB | 60k64k with q8 cache | 15tok/sest. | 189 tok/s | chat |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q4_K_M | fits | 14.0 GB | 37k67k with q8 cache | 15tok/sest. | 153 tok/s | chat |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 13.9 GB | 38k69k with q8 cache | 15tok/sest. | 220 tok/s | chat |
| Qwen 3.8 27B Alibaba Qwen | UD-Q4_K_M | offload | 18.8 GB | – | 7tok/sest. | 83 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q4_K_M | offload | 19.1 GB | – | 6tok/sest. | 82 tok/s | – |
| Gemma 4 31B | Q4_K_M | offload | 21.6 GB | – | 5tok/sest. | 68 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.4 GB | – | 14tok/sest. | 153 tok/s | chat |
| Qwen 3.6 35B-A3B Alibaba Qwen | MXFP4 | offload | 22.2 GB | – | 24tok/sest. | 538 tok/s | chat, coding |
| Qwen 3.5 27B Alibaba Qwen | Q4_K_M | offload | 19.0 GB | – | 6tok/sest. | 82 tok/s | – |
| Gemma 4 26B-A4B | MXFP4 | offload | 17.5 GB | – | 24tok/sest. | 546 tok/s | chat, coding |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q4_K_M | offload | 22.5 GB | – | 23tok/sest. | 534 tok/s | chat, coding |
| GLM 4.7 Flash Z.ai | Q4_K_M | offload | 20.0 GB | – | 14tok/sest. | 297 tok/s | chat |
| Devstral Small 2 24B Mistral AI | Q4_K_M | offload | 19.6 GB | 2k3k with q8 cache | 6tok/sest. | 85 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | MXFP4 | offload | 23.1 GB | – | 24tok/sest. | 600 tok/s | chat, coding, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | offload | 29.6 GB | – | 23tok/sest. | 404 tok/s | chat, coding |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q4_K_M | offload | 21.6 GB | – | 12tok/sest. | 251 tok/s | chat |
| Qwen3 32B Alibaba Qwen | Q4_K_M | offload | 27.7 GB | – | 3tok/sest. | 42 tok/s | – |
| Gemma 3 27B | Q4_K_M | offload | 19.6 GB | – | 6tok/sest. | 86 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q4_K_M | offload | 19.6 GB | 2k3k with q8 cache | 6tok/sest. | 85 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q4_K_M | offload | 27.8 GB | – | 3tok/sest. | 48 tok/s | – |
| Phi-4 14B Microsoft | Q4_K_M | offload | 15.8 GB | 16k | 11tok/sest. | 133 tok/s | chat |
| LFM2.5 24B A2B Liquid AI | Q4_K_M | offload | 18.1 GB | – | 20tok/sest. | 558 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q4_K_M | offload | 15.7 GB | 27k50k with q8 cache | 11tok/sest. | 125 tok/s | chat |
| Muse Glimmer 30B meta-models | Q4_K_M | offload | 17.9 GB | – | 7tok/sest. | 82 tok/s | – |
| Devstral Small 2507 Mistral AI | Q4_K_M | offload | 19.6 GB | 2k3k with q8 cache | 6tok/sest. | 86 tok/s | – |
| Magistral Small 2506 Mistral AI | Q4_K_M | offload | 19.6 GB | 2k3k with q8 cache | 6tok/sest. | 86 tok/s | – |
| Magistral Small 2507 Mistral AI | Q4_K_M | offload | 19.6 GB | 2k3k with q8 cache | 6tok/sest. | 86 tok/s | – |
| Magistral Small 2509 Mistral AI | Q4_K_M | offload | 19.6 GB | 2k3k with q8 cache | 6tok/sest. | 85 tok/s | – |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | offload | 22.7 GB | – | 4tok/sest. | 75 tok/s | – |
| granite 4.2 30b IBM | Q4_K_M | offload | 26.1 GB | – | 3tok/sest. | 57 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 94.2 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.0 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.6 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 79.2 GB | – | – | – | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | won't run | 41.1 GB | – | – | – | – |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | won't run | 52.6 GB | – | – | – | – |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | won't run | 47.3 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 60.9 GB | – | – | – | – |
| GLM 4.5 Air Z.ai | Q2_K | won't run | 49.2 GB | – | – | – | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | won't run | 47.3 GB | – | – | – | – |
| Llama 3.3 70B Meta | Q4_K_M | won't run | 50.9 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.6 GB | – | – | – | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | won't run | 50.9 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 380.1 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 381.0 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 381.0 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 381.0 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.6 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 158.4 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 82.0 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 214.4 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 66.3 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 213.6 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 72.6 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 214.4 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 386.4 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 424.0 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 437.9 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 750.4 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 71.2 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.6 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 582.0 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 582.0 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 582.0 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 137.9 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 137.9 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 124.3 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 244.7 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 82.0 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 32k context and generates at about 37 tok/s, an estimate from its memory bandwidth. 36 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 94 GB at 32k context, more than the NVIDIA GeForce RTX 5050 and system RAM can hold.
- How much does the NVIDIA GeForce RTX 5050 cost in Canada?
- The best new price for the NVIDIA GeForce RTX 5050 in Canada is $570 at Amazon.
Speeds on this page are for 32k context. See the best hardware for local AI at every budget.