AMD Radeon RX 7900 XTX vs AMD Radeon RX 9070 XT
For running models locally, priced in Canada. At 8k context the first runs 61 models fully in memory, the second 38.
In short
The AMD Radeon RX 7900 XTX has more memory for models: 24 GB against 16 GB. At 8k context the AMD Radeon RX 7900 XTX runs 61 of the models we track fully in memory and the AMD Radeon RX 9070 XT 38; only the AMD Radeon RX 7900 XTX holds Qwen 3.8 27B. On the models both run fully in memory, the AMD Radeon RX 7900 XTX is about 1.5× as fast as the AMD Radeon RX 9070 XT (estimated, median across models). In Canada the AMD Radeon RX 7900 XTX costs $1,407 at Amazon and the AMD Radeon RX 9070 XT $1,259 at Amazon: the AMD Radeon RX 9070 XT is $148 cheaper.
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | AMD Radeon RX 7900 XTX | AMD Radeon RX 9070 XT |
|---|---|---|
| GPU | Radeon RX 7900 XTX | Radeon RX 9070 XT |
| Memory | 24 GB GDDR6 | 16 GB GDDR6 |
| Memory bus | 384-bit | 256-bit |
| Memory bandwidth | 960 GB/s | 640 GB/s |
| FP16 compute | 123 TFLOPS | 195 TFLOPS |
| Software | ROCm | ROCm |
| Board power | 355 W | 304 W |
| PCIe generation | Gen 4 | Gen 5 |
| PCIe lanes | x16 | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | AMD Radeon RX 7900 XTX | AMD Radeon RX 9070 XT |
|---|---|---|
| Qwen 3.8 27B | 23tok/sUD-Q6_K | offload |
| Qwen 3.6 27B | 23tok/sQ6_K | offload |
| Gemma 4 31B | 23tok/sQ5_K_M | offload |
| Qwen 3.6 35B-A3B | 152tok/sQ4_K_M | offload |
| Qwen 3.5 27B | 23tok/sQ6_K | offload |
| Gemma 4 26B-A4B | 80tok/sUD-Q6_K | offload |
| Qwen 3.5 35B-A3B | 153tok/sQ4_K_M | offload |
| GLM 4.7 Flash | 79tok/sQ5_K_M | offload |
| Devstral Small 2 24B | 26tok/sQ6_K | offload |
| Nemotron 3.5 Lightning 30B-A3B | 138tok/sMXFP4 | offload |
| gpt-oss 20B | 120tok/sMXFP4 | 80tok/sMXFP4 |
| Qwen3 Coder 30B-A3B | 108tok/sQ5_K_M | offload |
| Qwen3 32B | 24tok/sQ4_K_M | offload |
| Gemma 4 12B | 40tok/sQ8_0 | 27tok/sQ8_0 |
| Qwen 3.5 9B | 54tok/sQ8_0 | 36tok/sQ8_0 |
| Mistral Small 3.2 24B | 26tok/sQ6_K | offload |
| DeepSeek R1 Distill Qwen 32B | 24tok/sQ4_K_M | offload |
| Gemma 3 27B | 23tok/sQ6_K | offload |
| Ministral 3 14B | 34tok/sQ8_0 | 28tok/sQ6_K |
| Qwen3 14B | 31tok/sQ8_0 | 26tok/sQ6_K |
| DeepSeek R1 0528 Qwen3 8B | 53tok/sQ8_0 | 36tok/sQ8_0 |
| Qwen3 8B | 53tok/sQ8_0 | 36tok/sQ8_0 |
| Phi-4 14B | 31tok/sQ8_0 | 26tok/sQ6_K |
| Qwen 3.5 4B | 110tok/sQ8_0 | 73tok/sQ8_0 |
| Ministral 3 8B | 52tok/sQ8_0 | 35tok/sQ8_0 |
| Granite 4.2 8B | 49tok/sQ8_0 | 33tok/sQ8_0 |
| Gemma 4 E4B | 62tok/sQ8_0 | 42tok/sQ8_0 |
| LFM2.5 8B-A1B | 216tok/sQ8_0 | 144tok/sQ8_0 |
| Llama 3.1 8B | 69tok/sQ6_K | 46tok/sQ6_K |
| Qwen2.5 0.5B | 836tok/sQ8_0 | 557tok/sQ8_0 |
| Qwen3.5 0.8B | 567tok/sQ8_0 | 378tok/sQ8_0 |
| Qwen3.5 2B | 340tok/sQ5_K_M | 226tok/sQ5_K_M |
| LFM3 1.7B | 270tok/sQ8_0 | 180tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 1.5B | 248tok/sQ8_0 | 165tok/sQ8_0 |
| MiniCPM5 2B | 174tok/sQ8_0 | 116tok/sQ8_0 |
| LFM2.5 2.6B | 156tok/sQ8_0 | 104tok/sQ8_0 |
| LFM2.5 VL 3B | 156tok/sQ8_0 | 104tok/sQ8_0 |
| Spark X2.5 4B | 155tok/smlx-4bit | 104tok/smlx-4bit |
| LFM2.5 24B A2B | 130tok/sQ6_K | offload |
| granite vision 4.1 4b | 123tok/sQ8_0 | 82tok/sQ8_0 |
| Ministral 3 3B Instruct 2512 | 117tok/sQ8_0 | 78tok/sQ8_0 |
| granite 4.2 3b | 116tok/sQ8_0 | 77tok/sQ8_0 |
| Mellum2.1 12B A2.5B Thinking | 112tok/sQ8_0 | 75tok/sQ8_0 |
| FrogNano 4B 2609 | 107tok/sQ8_0 | 71tok/sQ8_0 |
| Kimi VL A3B Thinking 2506 | 94tok/sQ8_0 | 97tok/sQ4_K_M |
| Kimi VL A3B | 90tok/smlx-8bit | 76tok/smlx-6bit |
| DeepSeek R1 Distill Qwen 7B | 62tok/sQ8_0 | 41tok/sQ8_0 |
| GLM 4 9B 0414 | 62tok/smlx-5bit | 41tok/smlx-5bit |
| DeepSeek R1 Distill Llama 8B | 55tok/sQ8_0 | 37tok/sQ8_0 |
| Ministral 3 8B Reasoning 2512 | 52tok/sQ8_0 | 35tok/sQ8_0 |
| GLM 4.6V Flash | 51tok/sQ8_0 | 34tok/sQ8_0 |
| GLM 4.1V 9B Thinking | 44tok/smlx-8bit | 29tok/smlx-8bit |
| Ministral 3 14B Reasoning 2512 | 34tok/sQ8_0 | 28tok/sQ6_K |
| DeepSeek R1 Distill Qwen 14B | 31tok/sQ8_0 | 26tok/sQ6_K |
| Devstral Small 2507 | 29tok/sQ5_K_M | offload |
| Magistral Small 2507 | 29tok/sQ5_K_M | offload |
| Magistral Small 2509 | 29tok/sQ5_K_M | offload |
| Magistral Small 2506 | 26tok/sQ6_K | offload |
| Qwen3.8 27B OBLITERATED | 25tok/smlx-4bit | offload |
| granite 4.2 30b | 23tok/sQ5_K_M | offload |
| Muse Glimmer 30B | 22tok/sQ6_K | offload |
| Qwen 3.5 122B-A10B | offload | offload |
| Qwen3 Coder Next | offload | won't run |
| Mistral Small 4 119B | offload | offload |
| GLM 4.5 Air | offload | won't run |
| Qwen3 Next 80B-A3B | offload | won't run |
| Kimi Linear 48B-A3B | offload | offload |
| Llama 3.3 70B | offload | won't run |
| DeepSeek R1 Distill Llama 70B | offload | won't run |
| 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 |
| gpt-oss 120B | 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 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 AMD Radeon RX 7900 XTX or the AMD Radeon RX 9070 XT?
- Choose the AMD Radeon RX 7900 XTX to run bigger models. Choose the AMD Radeon RX 7900 XTX for speed. Choose the AMD Radeon RX 9070 XT to spend less.
- Which can run bigger models, the AMD Radeon RX 7900 XTX or the AMD Radeon RX 9070 XT?
- At 8k context the AMD Radeon RX 7900 XTX runs 61 of the models we track fully in memory and the AMD Radeon RX 9070 XT 38; only the AMD Radeon RX 7900 XTX holds Qwen 3.8 27B.
- Which is faster for local AI, the AMD Radeon RX 7900 XTX or the AMD Radeon RX 9070 XT?
- On the models both run fully in memory, the AMD Radeon RX 7900 XTX is about 1.5× as fast as the AMD Radeon RX 9070 XT (estimated, median across models).
- What is the price difference between the AMD Radeon RX 7900 XTX and the AMD Radeon RX 9070 XT?
- In Canada the AMD Radeon RX 7900 XTX costs $1,407 at Amazon and the AMD Radeon RX 9070 XT $1,259 at Amazon: the AMD Radeon RX 9070 XT is $148 cheaper.
More comparisons
- Intel Arc Pro B60 vs AMD Radeon RX 7900 XTX
- AMD Radeon AI PRO R9700 vs AMD Radeon RX 7900 XTX
- NVIDIA GeForce RTX 3090 vs AMD Radeon RX 7900 XTX
- NVIDIA GeForce RTX 3090 Ti vs AMD Radeon RX 7900 XTX
- NVIDIA GeForce RTX 4070 Ti Super vs AMD Radeon RX 9070 XT
- NVIDIA GeForce RTX 4090 vs AMD Radeon RX 7900 XTX
- NVIDIA GeForce RTX 5070 vs AMD Radeon RX 9070 XT
- NVIDIA RTX PRO 2000 Blackwell vs AMD Radeon RX 9070 XT
- AMD Radeon RX 7600 XT vs AMD Radeon RX 7900 XTX
- AMD Radeon RX 7600 XT vs AMD Radeon RX 9070 XT