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 128k context it runs 66 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q8_0, at about 8 tok/s (estimated). We have no current price for the Intel Arc Pro B70 in the US.
Updated . Speeds are estimates; how they are worked out.
Prices
Every retailer we track in the US, cheapest first. Buy links may earn us a commission.
No retailer in this market lists it right now.
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 @128k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 37.2 GB | 256k | 8tok/sest. | 169 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q3_K_M | fits | 57.7 GB | 256k | 21tok/sest. | 300 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 8tok/sest. | 169 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q5_K_M | fits | 58.1 GB | 256k | 28tok/sest. | 666 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q3_K_M | fits | 60.7 GB | 253k256k with q8 cache | 23tok/sest. | 422 tok/s | chat, coding, long documents |
| Gemma 4 31B | Q8_0 | fits | 43.2 GB | 256k | 7tok/sest. | 160 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q3_K_M | fits | 55.5 GB | 375k596k with q8 cache | 27tok/sest. | 260 tok/s | chat, coding, agents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 39.0 GB | 256k | 29tok/sest. | 821 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 36.8 GB | 256k | 8tok/sest. | 169 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 29.8 GB | 256k | 24tok/sest. | 997 tok/s | chat, coding, agents, long documents |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q5_K_M | fits | 58.0 GB | 256k | 31tok/sest. | 728 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 39.0 GB | 256k | 29tok/sest. | 821 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 38.3 GB | 198k | 14tok/sest. | 387 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 45.4 GB | 232k384k with q8 cache | 7tok/sest. | 151 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 35.4 GB | 256k | 40tok/sest. | 1104 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 51.7 GB | 915k1024k with q8 cache | 39tok/sest. | 616 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 16.3 GB | 128k | 30tok/sest. | 645 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 44.3 GB | 256k | 10tok/sest. | 239 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q6_K | fits | 59.1 GB | 40k | 5tok/sest. | 68 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 16.2 GB | 256k | 20tok/sest. | 414 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 15.0 GB | 256k | 22tok/sest. | 493 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 39.2 GB | 128k | 8tok/sest. | 207 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 45.4 GB | 128k | 7tok/sest. | 151 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q6_K | fits | 59.1 GB | 128k | 5tok/sest. | 91 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 35.4 GB | 256k | 9tok/sest. | 194 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 36.7 GB | 40k | 8tok/sest. | 165 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 28.2 GB | 128k | 11tok/sest. | 250 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 28.2 GB | 40k | 11tok/sest. | 250 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 41.6 GB | 16k | 7tok/sest. | 166 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 10.3 GB | 256k | 34tok/sest. | 767 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 27.5 GB | 256k | 11tok/sest. | 253 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 30.8 GB | 128k | 10tok/sest. | 227 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 13.2 GB | 128k | 25tok/sest. | 691 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 16.4 GB | 125k | 22tok/sest. | 923 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 24.2 GB | 128k | 13tok/sest. | 273 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 4.0 GB | 32k | 142tok/sest. | 2074 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 4.3 GB | 256k | 125tok/sest. | 2766 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 4.9 GB | 256k | 99tok/sest. | 1769 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 7.3 GB | 128k | 54tok/sest. | 927 tok/s | chat, coding, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 9.4 GB | 1024k | 38tok/sest. | 759 tok/s | chat, coding, agents, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 9.8 GB | 128k | 37tok/sest. | 498 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 15.9 GB | 128k | 37tok/sest. | 1068 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 10.4 GB | 256k | 34tok/sest. | 767 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 12.2 GB | 128k | 28tok/sest. | 639 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 12.2 GB | 32k | 28tok/sest. | 615 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 21.7 GB | 128k | 23tok/sest. | 670 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 22.4 GB | 128k | 23tok/sest. | 670 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 14.7 GB | 32k | 22tok/sest. | 223 tok/s | chat, coding |
| granite vision 4.1 4b IBM | Q8_0 | fits | 15.4 GB | 128k | 21tok/sest. | 394 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 15.7 GB | 128k | 21tok/sest. | 402 tok/s | chat, coding, agents, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 16.4 GB | 128k | 20tok/sest. | 216 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 16.6 GB | 128k | 20tok/sest. | 331 tok/s | chat, coding, long documents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 18.0 GB | 64k | 18tok/sest. | 216 tok/s | chat, coding |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 18.5 GB | 256k | 17tok/sest. | 386 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 35.8 GB | 128k | 13tok/sest. | 539 tok/s | chat, coding, agents |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 26.0 GB | 128k | 12tok/sest. | 273 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 27.5 GB | 256k | 11tok/sest. | 253 tok/s | chat, coding |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 29.4 GB | 256k | 10tok/sest. | 169 tok/s | – |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 33.9 GB | 128k | 9tok/sest. | 184 tok/s | – |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 35.4 GB | 256k | 9tok/sest. | 194 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 40.7 GB | 128k | 7tok/sest. | 146 tok/s | chat |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 45.4 GB | 128k | 7tok/sest. | 153 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 45.4 GB | 40k | 7tok/sest. | 153 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 45.4 GB | 40k | 7tok/sest. | 153 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 45.4 GB | 128k | 7tok/sest. | 151 tok/s | – |
| granite 4.2 30b IBM | Q6_K | fits | 56.9 GB | 128k | 5tok/sest. | 108 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | offload | 78.6 GB | – | 3tok/sest. | 84 tok/s | – |
| gpt-oss 120B OpenAI | Q4_K_M | offload | 65.0 GB | 64k107k with q8 cache | 18tok/sest. | 434 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | offload | 67.3 GB | 101k128k with q8 cache | 4tok/sest. | 75 tok/s | chat |
| Llama 3.3 70B Meta | Q4_K_M | offload | 81.7 GB | 67k125k with q8 cache | 2tok/sest. | 38 tok/s | – |
| GLM 4.5V Z.ai | Q4_K_M | offload | 84.3 GB | 9k18k with q8 cache | 2tok/sest. | 65 tok/s | chat |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 81.7 GB | 67k125k with q8 cache | 2tok/sest. | 38 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 103.0 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 104.8 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 103.2 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 387.8 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 387.3 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 388.2 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 158.4 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 167.2 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 115.8 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 249.6 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 248.8 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 90.7 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 249.6 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 395.4 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 433.0 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 446.9 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 759.3 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 102.0 GB | 3k6k with q8 cache | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 588.8 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 589.2 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 161.9 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 161.9 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 148.3 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 256.7 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 115.8 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 128k context and generates at about 8 tok/s, an estimate from its memory bandwidth. 66 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 103 GB at 128k context, more than the Intel Arc Pro B70 and system RAM can hold.
- How much does the Intel Arc Pro B70 cost in the US?
- We have no current price for the Intel Arc Pro B70 in the US.
Speeds on this page are for 128k context. See the best hardware for local AI at every budget.