Intel Arc Pro B70
32 GB · 608 GB/s · 230 W
In short
The Intel Arc Pro B70 has 32 GB of GDDR6 memory with 608 GB/s of bandwidth, which sets how fast it generates text. At 8k context it runs 61 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q8_0, at about 10 tok/s (estimated). We have no current price for the Intel Arc Pro B70 in Germany.
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in Germany, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
What it runs
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 |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 28.5 GB | 46k82k with q8 cache | 10tok/sest. | 240 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 28.1 GB | 53k92k with q8 cache | 10tok/sest. | 240 tok/s | – |
| Gemma 4 31B | Q6_K | fits | 25.7 GB | 73k137k with q8 cache | 11tok/sest. | 210 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q6_K | fits | 29.9 GB | 59k93k with q8 cache | 59tok/sest. | 2060 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 28.1 GB | 53k92k with q8 cache | 10tok/sest. | 240 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.2 GB | 204k256k with q8 cache | 37tok/sest. | 1569 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 27.9 GB | 136k213k with q8 cache | 63tok/sest. | 2060 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 30.9 GB | 12k22k with q8 cache | 29tok/sest. | 1153 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 25.4 GB | 43k79k with q8 cache | 12tok/sest. | 271 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q5_K_M | fits | 29.1 GB | 189k246k with q8 cache | 56tok/sest. | 2146 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 28.9 GB | 174k237k with q8 cache | 86tok/sest. | 1958 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 12.3 GB | 128k | 64tok/sest. | 1491 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 25.0 GB | 70k126k with q8 cache | 51tok/sest. | 1490 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 27.9 GB | 20k38k with q8 cache | 11tok/sest. | 185 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.1 GB | 256k | 23tok/sest. | 547 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.0 GB | 256k | 31tok/sest. | 692 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 25.4 GB | 43k79k with q8 cache | 12tok/sest. | 271 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 27.9 GB | 20k38k with q8 cache | 11tok/sest. | 194 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 28.6 GB | 38k72k with q8 cache | 10tok/sest. | 244 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 15.5 GB | 105k191k with q8 cache | 19tok/sest. | 449 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 16.7 GB | 40k | 18tok/sest. | 418 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 10.1 GB | 128k | 31tok/sest. | 731 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 10.1 GB | 40k | 31tok/sest. | 731 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 16.9 GB | 16k | 18tok/sest. | 421 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 5.3 GB | 256k | 63tok/sest. | 1394 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 10.3 GB | 158k256k with q8 cache | 30tok/sest. | 683 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 10.8 GB | 128k | 28tok/sest. | 678 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 8.7 GB | 128k | 36tok/sest. | 839 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 9.6 GB | 125k | 114tok/sest. | 4898 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 8.0 GB | 128k | 40tok/sest. | 755 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.4 GB | 32k | 481tok/sest. | 10251 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 1.7 GB | 256k | 326tok/sest. | 7053 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.3 GB | 256k | 196tok/sest. | 2893 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 2.8 GB | 128k | 143tok/sest. | 3226 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 3.7 GB | 128k | 100tok/sest. | 2133 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 4.0 GB | 128k | 90tok/sest. | 2147 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 4.0 GB | 32k | 90tok/sest. | 1894 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 4.0 GB | 670k1024k with q8 cache | 89tok/sest. | 1518 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 4.8 GB | 128k | 71tok/sest. | 1421 tok/s | chat, coding, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 5.1 GB | 251k256k with q8 cache | 67tok/sest. | 1455 tok/s | chat, coding, agents, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 5.1 GB | 128k | 67tok/sest. | 1527 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 5.4 GB | 256k | 62tok/sest. | 1394 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 25.2 GB | 79k128k with q8 cache | 60tok/sest. | 2572 tok/s | chat, coding, agents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.0 GB | 128k | 59tok/sest. | 2360 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 16.9 GB | 128k | 50tok/sest. | 1990 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 17.7 GB | 128k | 48tok/sest. | 1990 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 8.8 GB | 128k | 36tok/sest. | 814 tok/s | chat, coding, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 8.8 GB | 32k | 35tok/sest. | 640 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 9.8 GB | 128k | 32tok/sest. | 755 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 10.3 GB | 158k256k with q8 cache | 30tok/sest. | 683 tok/s | chat, coding |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 10.5 GB | 128k | 29tok/sest. | 591 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 12.1 GB | 64k | 25tok/sest. | 591 tok/s | chat, coding |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 15.5 GB | 105k191k with q8 cache | 19tok/sest. | 449 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 17.0 GB | 81k128k with q8 cache | 18tok/sest. | 409 tok/s | chat |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 20.7 GB | 161k256k with q8 cache | 14tok/sest. | 240 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 25.4 GB | 43k79k with q8 cache | 12tok/sest. | 276 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 25.4 GB | 40k | 12tok/sest. | 276 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 25.4 GB | 40k | 12tok/sest. | 276 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 25.4 GB | 43k79k with q8 cache | 12tok/sest. | 271 tok/s | – |
| granite 4.2 30b IBM | Q6_K | fits | 25.7 GB | 29k54k with q8 cache | 11tok/sest. | 219 tok/s | – |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 31.1 GB | 10k18k with q8 cache | 9tok/sest. | 223 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.1 GB | – | 22tok/sest. | 549 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 46.3 GB | – | 25tok/sest. | 1286 tok/s | chat |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.0 GB | – | 10tok/sest. | 424 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 38.5 GB | – | 34tok/sest. | 735 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 44.5 GB | – | 10tok/sest. | 310 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 46.3 GB | – | 32tok/sest. | 1617 tok/s | chat, coding |
| Llama 3.3 70B Meta | Q4_K_M | offload | 42.9 GB | – | 3tok/sest. | 75 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 42.9 GB | – | 3tok/sest. | 75 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 91.7 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.3 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 74.6 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 72.9 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 59.6 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 378.0 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 378.5 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 378.0 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 378.0 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 378.0 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 378.9 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 378.9 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 378.9 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 147.2 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 155.9 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 73.4 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 205.3 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 61.5 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 204.5 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 67.9 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 205.3 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 383.9 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 421.5 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 435.4 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 747.9 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 63.3 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 579.5 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 580.0 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 580.0 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 580.0 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 131.6 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 131.6 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 118.1 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 241.5 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 73.4 GB | – | – | – | – |
Specifications
From the manufacturer's published specifications; sources are linked where we have them.
- GPU
- Arc Pro B70
- Memory
- 32 GB GDDR6
- Memory bus
- 256-bit
- Memory bandwidth
- 608 GB/s
- FP16 compute
- 45.8 TFLOPS
- Software
- SYCL / oneAPI
- Board power
- 230 W
- PCIe generation
- Gen 5
- PCIe lanes
- x16
Compare with
Questions
- How much memory does the Intel Arc Pro B70 have for AI models?
- The Intel Arc Pro B70 has 32 GB of GDDR6 memory with 608 GB/s of bandwidth, which sets how fast it generates text.
- What is the best model the Intel Arc Pro B70 can run locally?
- Qwen 3.8 27B (Q8_0) fits fully in its memory at 8k context and generates at about 10 tok/s, an estimate from its memory bandwidth. 61 of the 125 models we track fit at that context.
- Can the Intel Arc Pro B70 run DeepSeek V4 Flash?
- No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 92 GB at 8k context, more than the Intel Arc Pro B70 and system RAM can hold.
- How much does the Intel Arc Pro B70 cost in Germany?
- We have no current price for the Intel Arc Pro B70 in Germany.
Speeds on this page are for 8k context. See the best hardware for local AI at every budget.