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 32k 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 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 it runs
Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.
| Model | Quant | Fits | Memory | Max context | Decode @32k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 30.2 GB | 46k82k with q8 cache | 10tok/sest. | 222 tok/s | – |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 29.8 GB | 53k92k with q8 cache | 10tok/sest. | 222 tok/s | – |
| Gemma 4 31B | Q6_K | fits | 27.7 GB | 73k137k with q8 cache | 11tok/sest. | 197 tok/s | – |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q6_K | fits | 30.5 GB | 59k93k with q8 cache | 50tok/sest. | 1582 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 29.8 GB | 53k92k with q8 cache | 10tok/sest. | 222 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 26.8 GB | 204k256k with q8 cache | 33tok/sest. | 1408 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q6_K | fits | 28.5 GB | 136k213k with q8 cache | 53tok/sest. | 1582 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q6_K | fits | 25.6 GB | 128k198k with q8 cache | 29tok/sest. | 826 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 29.3 GB | 43k79k with q8 cache | 10tok/sest. | 234 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q5_K_M | fits | 29.4 GB | 189k246k with q8 cache | 54tok/sest. | 1805 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q4_K_M | fits | 29.3 GB | 174k237k with q8 cache | 78tok/sest. | 1364 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 13.0 GB | 128k | 52tok/sest. | 1181 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q6_K | fits | 27.4 GB | 70k126k with q8 cache | 29tok/sest. | 728 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q5_K_M | fits | 30.6 GB | 34k40k with q8 cache | 10tok/sest. | 138 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 13.6 GB | 256k | 22tok/sest. | 514 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 10.9 GB | 256k | 29tok/sest. | 640 tok/s | chat, coding, long documents |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 29.3 GB | 43k79k with q8 cache | 10tok/sest. | 234 tok/s | – |
| Gemma 3 27B | Q8_0 | fits | 30.6 GB | 38k72k with q8 cache | 10tok/sest. | 235 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q5_K_M | fits | 30.7 GB | 34k62k with q8 cache | 10tok/sest. | 158 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 19.4 GB | 105k191k with q8 cache | 15tok/sest. | 356 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 20.6 GB | 40k | 14tok/sest. | 320 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 13.6 GB | 128k | 22tok/sest. | 528 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 13.6 GB | 40k | 22tok/sest. | 528 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 21.7 GB | 16k | 14tok/sest. | 322 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 6.2 GB | 256k | 54tok/sest. | 1198 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 13.6 GB | 158k256k with q8 cache | 22tok/sest. | 510 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 14.7 GB | 128k | 21tok/sest. | 485 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 9.5 GB | 128k | 33tok/sest. | 805 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 10.9 GB | 125k | 63tok/sest. | 2632 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 11.1 GB | 128k | 28tok/sest. | 557 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 1.9 GB | 32k | 326tok/sest. | 5731 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 2.1 GB | 256k | 247tok/sest. | 5384 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 2.7 GB | 256k | 164tok/sest. | 2567 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 3.6 GB | 128k | 107tok/sest. | 2156 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 4.8 GB | 128k | 74tok/sest. | 1288 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 5.0 GB | 670k1024k with q8 cache | 71tok/sest. | 1264 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 5.5 GB | 128k | 62tok/sest. | 1459 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 5.5 GB | 32k | 62tok/sest. | 1337 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 6.3 GB | 256k | 53tok/sest. | 1198 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 13.5 GB | 128k | 53tok/sest. | 1900 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 6.9 GB | 128k | 48tok/sest. | 934 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 7.1 GB | 128k | 46tok/sest. | 979 tok/s | chat, coding, agents, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 7.6 GB | 251k256k with q8 cache | 43tok/sest. | 936 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 17.7 GB | 128k | 41tok/sest. | 1428 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 18.5 GB | 128k | 39tok/sest. | 1428 tok/s | chat, coding, agents, long documents |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 27.2 GB | 79k128k with q8 cache | 35tok/sest. | 1467 tok/s | chat, coding, agents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 9.9 GB | 32k | 32tok/sest. | 465 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 10.3 GB | 128k | 31tok/sest. | 630 tok/s | chat, coding, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 11.6 GB | 128k | 27tok/sest. | 439 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 12.9 GB | 128k | 24tok/sest. | 557 tok/s | chat, coding |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 13.2 GB | 64k | 23tok/sest. | 439 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 13.6 GB | 158k256k with q8 cache | 22tok/sest. | 510 tok/s | chat, coding |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 19.4 GB | 105k191k with q8 cache | 15tok/sest. | 356 tok/s | chat |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 21.6 GB | 81k128k with q8 cache | 14tok/sest. | 301 tok/s | chat |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 22.4 GB | 161k256k with q8 cache | 13tok/sest. | 222 tok/s | – |
| Muse Glimmer 30B meta-models | Q6_K | fits | 23.3 GB | 128k | 13tok/sest. | 214 tok/s | – |
| granite 4.2 30b IBM | Q5_K_M | fits | 28.6 GB | 42k78k with q8 cache | 10tok/sest. | 181 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 29.3 GB | 43k79k with q8 cache | 10tok/sest. | 237 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 29.3 GB | 40k | 10tok/sest. | 237 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 29.3 GB | 40k | 10tok/sest. | 237 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 29.3 GB | 43k79k with q8 cache | 10tok/sest. | 234 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | UD-Q2_K_XL | offload | 40.8 GB | – | 18tok/sest. | 444 tok/s | chat |
| Qwen3 Coder Next Alibaba Qwen | Q4_K_M | offload | 47.0 GB | – | 20tok/sest. | 994 tok/s | chat |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q2_K_XL | offload | 52.3 GB | – | 10tok/sest. | 396 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q2_K_XL | offload | 39.1 GB | – | 27tok/sest. | 506 tok/s | chat, coding |
| GLM 4.5 Air Z.ai | Q2_K | offload | 48.9 GB | – | 5tok/sest. | 167 tok/s | – |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q4_K_M | offload | 47.0 GB | – | 24tok/sest. | 1183 tok/s | chat, coding |
| Llama 3.3 70B Meta | Q4_K_M | offload | 50.6 GB | – | 2tok/sest. | 57 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | offload | 50.6 GB | – | 2tok/sest. | 57 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 93.9 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 102.7 GB | – | – | – | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | won't run | 75.3 GB | – | – | – | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | won't run | 78.9 GB | – | – | – | – |
| gpt-oss 120B OpenAI | Q4_K_M | won't run | 60.6 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 379.8 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 380.3 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 379.8 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 379.8 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 379.8 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 380.7 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 380.7 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 380.7 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 149.3 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 158.1 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 81.7 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 214.1 GB | – | – | – | – |
| GLM 4.5V Z.ai | Q4_K_M | won't run | 66.0 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 213.3 GB | – | – | – | – |
| GLM 4.6V Z.ai | Q4_K_M | won't run | 72.3 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 214.1 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 386.1 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 423.7 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 437.6 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 750.1 GB | – | – | – | – |
| Kimi Dev 72B Moonshot AI | Q6_K | won't run | 70.9 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 581.3 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 581.7 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 581.7 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 581.7 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 137.6 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 137.6 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 124.0 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 244.4 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 81.7 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 32k 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 94 GB at 32k 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 32k context. See the best hardware for local AI at every budget.