NVIDIA GeForce RTX 5080 vs AMD Radeon RX 9070
For running models locally, priced in Canada. At 32k context the first runs 36 models fully in memory, the second 35.
In short
Both have 16 GB of memory for models; the NVIDIA GeForce RTX 5080 has 960 GB/s of bandwidth and the AMD Radeon RX 9070 640 GB/s. At 32k context the NVIDIA GeForce RTX 5080 runs 36 of the models we track fully in memory and the AMD Radeon RX 9070 35; only the NVIDIA GeForce RTX 5080 holds DeepSeek R1 Distill Qwen 14B. On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.7× as fast as the AMD Radeon RX 9070 (estimated, median across models). In Canada the NVIDIA GeForce RTX 5080 costs $2,580 at Amazon and the AMD Radeon RX 9070 $1,074 at Amazon: the AMD Radeon RX 9070 is $1,506 cheaper.
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | NVIDIA GeForce RTX 5080 | AMD Radeon RX 9070 |
|---|---|---|
| GPU | GeForce RTX 5080 | Radeon RX 9070 |
| Memory | 16 GB GDDR7 | 16 GB GDDR6 |
| Memory bus | 256-bit | 256-bit |
| Memory bandwidth | 960 GB/s | 640 GB/s |
| FP16 compute | 113 TFLOPS | 36.1 TFLOPS |
| Software | CUDA | ROCm |
| Board power | 360 W | 220 W |
| PCIe generation | Gen 5 | Gen 5 |
| PCIe lanes | x16 | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | NVIDIA GeForce RTX 5080 | AMD Radeon RX 9070 |
|---|---|---|
| gpt-oss 20B | 110tok/sMXFP4 | 65tok/sMXFP4 |
| Gemma 4 12B | 44tok/sQ8_0 | 26tok/sQ8_0 |
| Qwen 3.5 9B | 56tok/sQ8_0 | 33tok/sQ8_0 |
| Qwen3 14B | 41tok/sQ4_K_M | 25tok/sQ4_K_M |
| Ministral 3 14B | 40tok/sQ5_K_M | 24tok/sQ5_K_M |
| DeepSeek R1 0528 Qwen3 8B | 44tok/sQ8_0 | 26tok/sQ8_0 |
| Qwen3 8B | 44tok/sQ8_0 | 26tok/sQ8_0 |
| Qwen 3.5 4B | 106tok/sQ8_0 | 63tok/sQ8_0 |
| Ministral 3 8B | 44tok/sQ8_0 | 26tok/sQ8_0 |
| Granite 4.2 8B | 41tok/sQ8_0 | 24tok/sQ8_0 |
| Gemma 4 E4B | 65tok/sQ8_0 | 38tok/sQ8_0 |
| LFM2.5 8B-A1B | 134tok/sQ8_0 | 79tok/sQ8_0 |
| Llama 3.1 8B | 55tok/sQ6_K | 32tok/sQ6_K |
| Qwen2.5 0.5B | 637tok/sQ8_0 | 377tok/sQ8_0 |
| Qwen3.5 0.8B | 483tok/sQ8_0 | 285tok/sQ8_0 |
| Qwen3.5 2B | 321tok/sQ5_K_M | 190tok/sQ5_K_M |
| DeepSeek R1 Distill Qwen 1.5B | 210tok/sQ8_0 | 124tok/sQ8_0 |
| MiniCPM5 2B | 146tok/sQ8_0 | 86tok/sQ8_0 |
| Spark X2.5 4B | 138tok/smlx-4bit | 82tok/smlx-4bit |
| LFM2.5 2.6B | 122tok/sQ8_0 | 72tok/sQ8_0 |
| LFM2.5 VL 3B | 122tok/sQ8_0 | 72tok/sQ8_0 |
| Kimi VL A3B Thinking 2506 | 121tok/sQ4_K_M | 72tok/sQ4_K_M |
| Mellum2.1 12B A2.5B Thinking | 113tok/sQ8_0 | 67tok/sQ8_0 |
| FrogNano 4B 2609 | 104tok/sQ8_0 | 61tok/sQ8_0 |
| Kimi VL A3B | 101tok/smlx-6bit | 60tok/smlx-6bit |
| granite vision 4.1 4b | 94tok/sQ8_0 | 56tok/sQ8_0 |
| granite 4.2 3b | 91tok/sQ8_0 | 54tok/sQ8_0 |
| Ministral 3 3B Instruct 2512 | 83tok/sQ8_0 | 49tok/sQ8_0 |
| GLM 4 9B 0414 | 62tok/smlx-5bit | 37tok/smlx-5bit |
| DeepSeek R1 Distill Qwen 7B | 60tok/sQ8_0 | 35tok/sQ8_0 |
| GLM 4.6V Flash | 53tok/sQ8_0 | 31tok/sQ8_0 |
| DeepSeek R1 Distill Llama 8B | 46tok/sQ8_0 | 27tok/sQ8_0 |
| GLM 4.1V 9B Thinking | 45tok/smlx-8bit | 27tok/smlx-8bit |
| Ministral 3 8B Reasoning 2512 | 44tok/sQ8_0 | 26tok/sQ8_0 |
| Ministral 3 14B Reasoning 2512 | 40tok/sQ5_K_M | 24tok/sQ5_K_M |
| DeepSeek R1 Distill Qwen 14B | 39tok/sQ4_K_M | offload |
| Qwen 3.8 27B | offload | offload |
| Qwen 3.5 122B-A10B | offload | offload |
| Qwen 3.6 27B | offload | offload |
| Gemma 4 31B | offload | offload |
| Mistral Small 4 119B | offload | offload |
| Qwen 3.6 35B-A3B | offload | offload |
| Qwen 3.5 27B | offload | offload |
| Gemma 4 26B-A4B | offload | offload |
| Qwen 3.5 35B-A3B | offload | offload |
| GLM 4.7 Flash | offload | offload |
| Devstral Small 2 24B | offload | offload |
| Nemotron 3.5 Lightning 30B-A3B | offload | offload |
| Kimi Linear 48B-A3B | offload | offload |
| Qwen3 Coder 30B-A3B | offload | offload |
| Qwen3 32B | offload | offload |
| Gemma 3 27B | offload | offload |
| Mistral Small 3.2 24B | offload | offload |
| DeepSeek R1 Distill Qwen 32B | offload | offload |
| Phi-4 14B | offload | offload |
| LFM2.5 24B A2B | offload | offload |
| Muse Glimmer 30B | offload | offload |
| Devstral Small 2507 | offload | offload |
| Magistral Small 2506 | offload | offload |
| Magistral Small 2507 | offload | offload |
| Magistral Small 2509 | offload | offload |
| Qwen3.8 27B OBLITERATED | offload | offload |
| granite 4.2 30b | offload | offload |
| DeepSeek V4 Flash | won't run | won't run |
| GLM 5.3 Flash | won't run | won't run |
| Qwen 3.8 Flash Next | won't run | won't run |
| MiniMax M2.7 | won't run | won't run |
| Nemotron 3 Super 120B-A12B | won't run | won't run |
| Qwen3 Coder Next | won't run | won't run |
| gpt-oss 120B | won't run | won't run |
| GLM 4.5 Air | won't run | won't run |
| Qwen3 Next 80B-A3B | won't run | won't run |
| Llama 3.3 70B | won't run | won't run |
| DeepSeek R1 | won't run | won't run |
| DeepSeek R1 0528 | won't run | won't run |
| DeepSeek R1 Distill Llama 70B | won't run | won't run |
| DeepSeek R1 Zero | won't run | won't run |
| DeepSeek V3 | won't run | won't run |
| DeepSeek V3 0324 | won't run | won't run |
| DeepSeek V3.1 | won't run | won't run |
| DeepSeek V3.1 Terminus | won't run | won't run |
| DeepSeek V3.2 | won't run | won't run |
| DeepSeek V4 Flash 0731 | won't run | won't run |
| DeepSeek V4 Flash Vision Exp | won't run | won't run |
| Devstral 2 123B Instruct 2512 | won't run | won't run |
| GLM 4.5 | won't run | won't run |
| GLM 4.5V | won't run | won't run |
| GLM 4.6 | won't run | won't run |
| GLM 4.6V | won't run | won't run |
| GLM 4.7 | won't run | won't run |
| GLM 5 | won't run | won't run |
| GLM 5.1 | won't run | won't run |
| GLM 5.2 | won't run | won't run |
| GLM 5.3 | won't run | won't run |
| Kimi Dev 72B | won't run | won't run |
| Kimi K2 | won't run | won't run |
| Kimi K2 Instruct 0905 | won't run | won't run |
| Kimi K2 Thinking | won't run | won't run |
| Kimi K2.5 | won't run | won't run |
| MiniMax M2 | won't run | won't run |
| MiniMax M2.1 | won't run | won't run |
| MiniMax M2.5 | won't run | won't run |
| MiniMax M3 | won't run | won't run |
| Mistral Medium 3.5 128B | won't run | won't run |
Questions
- Which is better for local AI, the NVIDIA GeForce RTX 5080 or the AMD Radeon RX 9070?
- Choose the NVIDIA GeForce RTX 5080 to run bigger models. Choose the NVIDIA GeForce RTX 5080 for speed. Choose the AMD Radeon RX 9070 to spend less.
- Which can run bigger models, the NVIDIA GeForce RTX 5080 or the AMD Radeon RX 9070?
- At 32k context the NVIDIA GeForce RTX 5080 runs 36 of the models we track fully in memory and the AMD Radeon RX 9070 35; only the NVIDIA GeForce RTX 5080 holds DeepSeek R1 Distill Qwen 14B.
- Which is faster for local AI, the NVIDIA GeForce RTX 5080 or the AMD Radeon RX 9070?
- On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.7× as fast as the AMD Radeon RX 9070 (estimated, median across models).
- What is the price difference between the NVIDIA GeForce RTX 5080 and the AMD Radeon RX 9070?
- In Canada the NVIDIA GeForce RTX 5080 costs $2,580 at Amazon and the AMD Radeon RX 9070 $1,074 at Amazon: the AMD Radeon RX 9070 is $1,506 cheaper.
More comparisons
- Intel Arc A770 16GB vs AMD Radeon RX 9070
- Intel Arc Pro B70 vs NVIDIA GeForce RTX 5080
- Mac mini M4 16GB vs AMD Radeon RX 9070
- AMD Radeon AI PRO R9700 vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 4070 Ti Super vs AMD Radeon RX 9070
- NVIDIA GeForce RTX 4080 Super vs NVIDIA GeForce RTX 5080
- NVIDIA GeForce RTX 4080 Super vs AMD Radeon RX 9070
- NVIDIA GeForce RTX 5060 Ti 16GB vs AMD Radeon RX 9070
- NVIDIA GeForce RTX 5070 Ti vs NVIDIA GeForce RTX 5080