Intel Arc Pro B70 vs AMD Radeon RX 7900 XT
For running models locally, priced in the US. At 8k context the first runs 61 models fully in memory, the second 52.
In short
The Intel Arc Pro B70 has more memory for models: 32 GB against 20 GB. At 8k context the Intel Arc Pro B70 runs 61 of the models we track fully in memory and the AMD Radeon RX 7900 XT 52; only the Intel Arc Pro B70 holds Gemma 4 31B. On the models both run fully in memory, the AMD Radeon RX 7900 XT is about 1.4× as fast as the Intel Arc Pro B70 (estimated, median across models).
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | Intel Arc Pro B70 | AMD Radeon RX 7900 XT |
|---|---|---|
| GPU | Arc Pro B70 | Radeon RX 7900 XT |
| Memory | 32 GB GDDR6 | 20 GB GDDR6 |
| Memory bus | 256-bit | 320-bit |
| Memory bandwidth | 608 GB/s | 800 GB/s |
| FP16 compute | 45.8 TFLOPS | 103 TFLOPS |
| Software | SYCL / oneAPI | ROCm |
| Board power | 230 W | 315 W |
| PCIe generation | Gen 5 | Gen 4 |
| PCIe lanes | x16 | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | Intel Arc Pro B70 | AMD Radeon RX 7900 XT |
|---|---|---|
| Qwen 3.8 27B | 10tok/sQ8_0 | 24tok/sQ4_K_M |
| Qwen 3.6 27B | 10tok/sQ8_0 | 25tok/sQ4_K_M |
| Gemma 4 31B | 11tok/sQ6_K | offload |
| Qwen 3.6 35B-A3B | 59tok/sQ6_K | offload |
| Qwen 3.5 27B | 10tok/sQ8_0 | 25tok/sQ4_K_M |
| Gemma 4 26B-A4B | 37tok/sQ8_0 | 78tok/sQ5_K_M |
| Qwen 3.5 35B-A3B | 63tok/sQ6_K | offload |
| GLM 4.7 Flash | 29tok/sQ8_0 | 76tok/sQ4_K_M |
| Devstral Small 2 24B | 12tok/sQ8_0 | 24tok/sQ5_K_M |
| Nemotron 3.5 Lightning 30B-A3B | 56tok/sUD-Q5_K_M | offload |
| Kimi Linear 48B-A3B | 86tok/sQ4_K_M | offload |
| gpt-oss 20B | 64tok/sMXFP4 | 100tok/sMXFP4 |
| Qwen3 Coder 30B-A3B | 51tok/sQ6_K | 100tok/sQ4_K_M |
| Qwen3 32B | 11tok/sQ6_K | offload |
| Gemma 4 12B | 23tok/sQ8_0 | 34tok/sQ8_0 |
| Qwen 3.5 9B | 31tok/sQ8_0 | 45tok/sQ8_0 |
| Mistral Small 3.2 24B | 12tok/sQ8_0 | 24tok/sQ5_K_M |
| DeepSeek R1 Distill Qwen 32B | 11tok/sQ6_K | offload |
| Gemma 3 27B | 10tok/sQ8_0 | 25tok/sQ4_K_M |
| Ministral 3 14B | 19tok/sQ8_0 | 28tok/sQ8_0 |
| Qwen3 14B | 18tok/sQ8_0 | 26tok/sQ8_0 |
| DeepSeek R1 0528 Qwen3 8B | 31tok/sQ8_0 | 44tok/sQ8_0 |
| Qwen3 8B | 31tok/sQ8_0 | 44tok/sQ8_0 |
| Phi-4 14B | 18tok/sQ8_0 | 26tok/sQ8_0 |
| Qwen 3.5 4B | 63tok/sQ8_0 | 92tok/sQ8_0 |
| Ministral 3 8B | 30tok/sQ8_0 | 43tok/sQ8_0 |
| Granite 4.2 8B | 28tok/sQ8_0 | 41tok/sQ8_0 |
| Gemma 4 E4B | 36tok/sQ8_0 | 52tok/sQ8_0 |
| LFM2.5 8B-A1B | 114tok/sQ8_0 | 180tok/sQ8_0 |
| Llama 3.1 8B | 40tok/sQ6_K | 57tok/sQ6_K |
| Qwen2.5 0.5B | 481tok/sQ8_0 | 697tok/sQ8_0 |
| Qwen3.5 0.8B | 326tok/sQ8_0 | 472tok/sQ8_0 |
| Qwen3.5 2B | 196tok/sQ5_K_M | 283tok/sQ5_K_M |
| DeepSeek R1 Distill Qwen 1.5B | 143tok/sQ8_0 | 207tok/sQ8_0 |
| MiniCPM5 2B | 100tok/sQ8_0 | 145tok/sQ8_0 |
| LFM2.5 2.6B | 90tok/sQ8_0 | 130tok/sQ8_0 |
| LFM2.5 VL 3B | 90tok/sQ8_0 | 130tok/sQ8_0 |
| Spark X2.5 4B | 89tok/smlx-4bit | 130tok/smlx-4bit |
| granite vision 4.1 4b | 71tok/sQ8_0 | 103tok/sQ8_0 |
| Ministral 3 3B Instruct 2512 | 67tok/sQ8_0 | 97tok/sQ8_0 |
| granite 4.2 3b | 67tok/sQ8_0 | 96tok/sQ8_0 |
| FrogNano 4B 2609 | 62tok/sQ8_0 | 89tok/sQ8_0 |
| LFM2.5 24B A2B | 60tok/sQ8_0 | 119tok/sQ5_K_M |
| Mellum2.1 12B A2.5B Thinking | 59tok/sQ8_0 | 94tok/sQ8_0 |
| Kimi VL A3B Thinking 2506 | 50tok/sQ8_0 | 79tok/sQ8_0 |
| Kimi VL A3B | 48tok/smlx-8bit | 75tok/smlx-8bit |
| DeepSeek R1 Distill Qwen 7B | 36tok/sQ8_0 | 51tok/sQ8_0 |
| GLM 4 9B 0414 | 35tok/smlx-5bit | 51tok/smlx-5bit |
| DeepSeek R1 Distill Llama 8B | 32tok/sQ8_0 | 46tok/sQ8_0 |
| Ministral 3 8B Reasoning 2512 | 30tok/sQ8_0 | 43tok/sQ8_0 |
| GLM 4.6V Flash | 29tok/sQ8_0 | 43tok/sQ8_0 |
| GLM 4.1V 9B Thinking | 25tok/smlx-8bit | 36tok/smlx-8bit |
| Ministral 3 14B Reasoning 2512 | 19tok/sQ8_0 | 28tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 14B | 18tok/sQ8_0 | 25tok/sQ8_0 |
| Qwen3.8 27B OBLITERATED | 14tok/smlx-4bit | offload |
| Devstral Small 2507 | 12tok/sQ8_0 | 24tok/sQ5_K_M |
| Magistral Small 2506 | 12tok/sQ8_0 | 24tok/sQ5_K_M |
| Magistral Small 2507 | 12tok/sQ8_0 | 24tok/sQ5_K_M |
| Magistral Small 2509 | 12tok/sQ8_0 | 24tok/sQ5_K_M |
| granite 4.2 30b | 11tok/sQ6_K | offload |
| Muse Glimmer 30B | 9tok/sQ8_0 | 25tok/sQ4_K_M |
| Qwen 3.5 122B-A10B | offload | offload |
| Qwen3 Coder Next | offload | won't run |
| Nemotron 3 Super 120B-A12B | offload | won't run |
| Mistral Small 4 119B | offload | offload |
| GLM 4.5 Air | offload | offload |
| Qwen3 Next 80B-A3B | offload | won't run |
| Llama 3.3 70B | offload | offload |
| DeepSeek R1 Distill Llama 70B | 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 |
| 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 Intel Arc Pro B70 or the AMD Radeon RX 7900 XT?
- Choose the Intel Arc Pro B70 to run bigger models. Choose the AMD Radeon RX 7900 XT for speed.
- Which can run bigger models, the Intel Arc Pro B70 or the AMD Radeon RX 7900 XT?
- At 8k context the Intel Arc Pro B70 runs 61 of the models we track fully in memory and the AMD Radeon RX 7900 XT 52; only the Intel Arc Pro B70 holds Gemma 4 31B.
- Which is faster for local AI, the Intel Arc Pro B70 or the AMD Radeon RX 7900 XT?
- On the models both run fully in memory, the AMD Radeon RX 7900 XT is about 1.4× as fast as the Intel Arc Pro B70 (estimated, median across models).
More comparisons
- Intel Arc Pro B60 vs Intel Arc Pro B70
- Intel Arc Pro B70 vs AMD Radeon AI PRO R9700
- Intel Arc Pro B70 vs NVIDIA RTX PRO 4000 Blackwell
- Mac mini M4 16GB vs AMD Radeon RX 7900 XT
- NVIDIA GeForce RTX 4060 Ti 16GB vs AMD Radeon RX 7900 XT
- NVIDIA GeForce RTX 4070 Super vs AMD Radeon RX 7900 XT
- NVIDIA GeForce RTX 4080 Super vs AMD Radeon RX 7900 XT
- NVIDIA GeForce RTX 5070 Ti vs AMD Radeon RX 7900 XT
- AMD Radeon RX 7600 XT vs AMD Radeon RX 7900 XT
- AMD Radeon RX 7800 XT vs AMD Radeon RX 7900 XT