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 64k context it runs 70 of the 125 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q8_0, at about 9 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 @64k | Prefill | Good for |
|---|---|---|---|---|---|---|---|
| Qwen 3.8 27B Alibaba Qwen | Q8_0 | fits | 32.9 GB | 256k | 9tok/sest. | 201 tok/s | – |
| Qwen 3.5 122B-A10B Alibaba Qwen | Q3_K_M | fits | 55.9 GB | 256k | 27tok/sest. | 418 tok/s | chat, coding, agents, long documents |
| Qwen 3.6 27B Alibaba Qwen | Q8_0 | fits | 32.4 GB | 256k | 9tok/sest. | 201 tok/s | – |
| Qwen3 Coder Next Alibaba Qwen | Q5_K_M | fits | 56.2 GB | 256k | 38tok/sest. | 968 tok/s | chat, coding, agents, long documents |
| gpt-oss 120B OpenAI | Q4_K_M | fits | 62.4 GB | 64k107k with q8 cache | 30tok/sest. | 648 tok/s | chat, coding, agents, long documents |
| Nemotron 3 Super 120B-A12B NVIDIA | UD-Q3_K_M | fits | 59.8 GB | 253k256k with q8 cache | 25tok/sest. | 486 tok/s | chat, coding, long documents |
| Gemma 4 31B | Q8_0 | fits | 37.9 GB | 256k | 8tok/sest. | 183 tok/s | – |
| Mistral Small 4 119B Mistral AI | UD-Q3_K_M | fits | 53.7 GB | 375k596k with q8 cache | 35tok/sest. | 411 tok/s | chat, coding, agents |
| Qwen 3.6 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.4 GB | 256k | 37tok/sest. | 1209 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 27B Alibaba Qwen | Q8_0 | fits | 32.4 GB | 256k | 9tok/sest. | 201 tok/s | – |
| Gemma 4 26B-A4B | Q8_0 | fits | 28.1 GB | 256k | 29tok/sest. | 1237 tok/s | chat, coding, agents, long documents |
| GLM 4.5 Air Z.ai | Q2_K | fits | 55.4 GB | 101k128k with q8 cache | 9tok/sest. | 136 tok/s | chat |
| Qwen3 Next 80B-A3B Alibaba Qwen | Q5_K_M | fits | 56.2 GB | 256k | 44tok/sest. | 1104 tok/s | chat, coding, agents, long documents |
| Qwen 3.5 35B-A3B Alibaba Qwen | Q8_0 | fits | 37.4 GB | 256k | 37tok/sest. | 1209 tok/s | chat, coding, agents, long documents |
| GLM 4.7 Flash Z.ai | Q8_0 | fits | 34.6 GB | 198k | 19tok/sest. | 600 tok/s | chat, coding |
| Devstral Small 2 24B Mistral AI | Q8_0 | fits | 35.0 GB | 232k384k with q8 cache | 9tok/sest. | 198 tok/s | – |
| Nemotron 3.5 Lightning 30B-A3B NVIDIA | UD-Q6_K_XL | fits | 34.7 GB | 256k | 44tok/sest. | 1490 tok/s | chat, coding, agents, long documents |
| Kimi Linear 48B-A3B Moonshot AI | Q8_0 | fits | 50.9 GB | 915k1024k with q8 cache | 45tok/sest. | 971 tok/s | chat, coding, long documents |
| gpt-oss 20B OpenAI | MXFP4 | fits | 14.5 GB | 128k | 41tok/sest. | 925 tok/s | chat, coding, agents, long documents |
| Qwen3 Coder 30B-A3B Alibaba Qwen | Q8_0 | fits | 37.9 GB | 256k | 17tok/sest. | 433 tok/s | chat, coding |
| Qwen3 32B Alibaba Qwen | Q8_0 | fits | 50.1 GB | 40k | 6tok/sest. | 102 tok/s | – |
| Gemma 4 12B | Q8_0 | fits | 14.8 GB | 256k | 22tok/sest. | 476 tok/s | chat, coding, long documents |
| Qwen 3.5 9B Alibaba Qwen | Q8_0 | fits | 12.6 GB | 256k | 26tok/sest. | 582 tok/s | chat, coding, long documents |
| Gemma 3 27B | Q8_0 | fits | 33.8 GB | 128k | 9tok/sest. | 225 tok/s | – |
| Mistral Small 3.2 24B Mistral AI | Q8_0 | fits | 35.0 GB | 128k | 9tok/sest. | 198 tok/s | – |
| DeepSeek R1 Distill Qwen 32B DeepSeek | Q8_0 | fits | 50.1 GB | 112k128k with q8 cache | 6tok/sest. | 127 tok/s | – |
| Llama 3.3 70B Meta | Q4_K_M | fits | 61.3 GB | 67k125k with q8 cache | 5tok/sest. | 61 tok/s | – |
| Ministral 3 14B Mistral AI | Q8_0 | fits | 25.0 GB | 256k | 12tok/sest. | 278 tok/s | chat |
| Qwen3 14B Alibaba Qwen | Q8_0 | fits | 26.3 GB | 40k | 12tok/sest. | 244 tok/s | chat |
| DeepSeek R1 0528 Qwen3 8B DeepSeek | Q8_0 | fits | 18.8 GB | 128k | 17tok/sest. | 385 tok/s | chat, coding |
| Qwen3 8B Alibaba Qwen | Q8_0 | fits | 18.8 GB | 40k | 17tok/sest. | 385 tok/s | chat, coding |
| Phi-4 14B Microsoft | Q8_0 | fits | 28.7 GB | 16k | 11tok/sest. | 245 tok/s | chat |
| Qwen 3.5 4B Alibaba Qwen | Q8_0 | fits | 7.9 GB | 256k | 46tok/sest. | 1009 tok/s | chat, coding, long documents |
| Ministral 3 8B Mistral AI | Q8_0 | fits | 18.6 GB | 256k | 17tok/sest. | 381 tok/s | chat, coding |
| Granite 4.2 8B IBM | Q8_0 | fits | 20.4 GB | 128k | 15tok/sest. | 352 tok/s | chat, coding |
| Gemma 4 E4B | Q8_0 | fits | 11.1 GB | 128k | 30tok/sest. | 763 tok/s | chat, coding, long documents |
| LFM2.5 8B-A1B Liquid AI | Q8_0 | fits | 13.1 GB | 125k | 39tok/sest. | 1628 tok/s | chat, coding, long documents |
| Llama 3.1 8B Meta | Q6_K | fits | 15.8 GB | 128k | 20tok/sest. | 413 tok/s | chat, coding |
| Qwen2.5 0.5B Alibaba Qwen | Q8_0 | fits | 2.9 GB | 32k | 228tok/sest. | 3610 tok/s | chat, coding, long documents |
| Qwen3.5 0.8B Alibaba Qwen | Q8_0 | fits | 3.2 GB | 256k | 186tok/sest. | 4092 tok/s | chat, coding, agents, long documents |
| Qwen3.5 2B Alibaba Qwen | Q5_K_M | fits | 3.8 GB | 256k | 135tok/sest. | 2231 tok/s | chat, coding, agents, long documents |
| DeepSeek R1 Distill Qwen 1.5B DeepSeek | Q8_0 | fits | 5.2 GB | 128k | 81tok/sest. | 1495 tok/s | chat, coding, long documents |
| MiniCPM5 2B openbmb | Q8_0 | fits | 6.8 GB | 128k | 55tok/sest. | 843 tok/s | chat, coding, agents, long documents |
| Spark X2.5 4B XHToken | mlx-4bit | fits | 6.8 GB | 1024k | 55tok/sest. | 1034 tok/s | chat, coding, agents, long documents |
| Mellum2.1 12B A2.5B Thinking JetBrains | Q8_0 | fits | 14.6 GB | 128k | 46tok/sest. | 1508 tok/s | chat, coding, agents, long documents |
| FrogNano 4B 2609 Microsoft | Q8_0 | fits | 8.0 GB | 256k | 45tok/sest. | 1009 tok/s | chat, coding, agents, long documents |
| LFM2.5 2.6B Liquid AI | Q8_0 | fits | 8.1 GB | 128k | 44tok/sest. | 1022 tok/s | chat, coding, agents, long documents |
| LFM2.5 VL 3B Liquid AI | Q8_0 | fits | 8.1 GB | 32k | 44tok/sest. | 961 tok/s | chat, coding, agents, long documents |
| granite vision 4.1 4b IBM | Q8_0 | fits | 10.0 GB | 128k | 34tok/sest. | 642 tok/s | chat, coding, long documents |
| granite 4.2 3b IBM | Q8_0 | fits | 10.3 GB | 128k | 33tok/sest. | 662 tok/s | chat, coding, agents, long documents |
| Kimi VL A3B Thinking 2506 Moonshot AI | Q8_0 | fits | 19.4 GB | 128k | 33tok/sest. | 1037 tok/s | chat, coding, long documents |
| Kimi VL A3B Moonshot AI | mlx-8bit | fits | 20.2 GB | 128k | 32tok/sest. | 1037 tok/s | chat, coding, agents, long documents |
| Ministral 3 3B Instruct 2512 Mistral AI | Q8_0 | fits | 11.6 GB | 256k | 29tok/sest. | 634 tok/s | chat, coding, agents, long documents |
| GLM 4 9B 0414 Z.ai | mlx-5bit | fits | 11.9 GB | 32k | 28tok/sest. | 341 tok/s | chat, coding |
| DeepSeek R1 Distill Qwen 7B DeepSeek | Q8_0 | fits | 12.7 GB | 128k | 26tok/sest. | 484 tok/s | chat, coding, long documents |
| GLM 4.6V Flash Z.ai | Q8_0 | fits | 13.5 GB | 128k | 24tok/sest. | 327 tok/s | chat, coding |
| LFM2.5 24B A2B Liquid AI | Q8_0 | fits | 30.4 GB | 128k | 22tok/sest. | 932 tok/s | chat, coding, agents |
| GLM 4.1V 9B Thinking Z.ai | mlx-8bit | fits | 15.1 GB | 64k | 21tok/sest. | 327 tok/s | chat, coding |
| DeepSeek R1 Distill Llama 8B DeepSeek | Q8_0 | fits | 17.6 GB | 128k | 18tok/sest. | 413 tok/s | chat, coding |
| Ministral 3 8B Reasoning 2512 Mistral AI | Q8_0 | fits | 18.6 GB | 256k | 17tok/sest. | 381 tok/s | chat, coding |
| Ministral 3 14B Reasoning 2512 Mistral AI | Q8_0 | fits | 25.0 GB | 256k | 12tok/sest. | 278 tok/s | chat |
| Qwen3.8 27B OBLITERATED OBLITERATUS | mlx-4bit | fits | 25.1 GB | 256k | 12tok/sest. | 201 tok/s | – |
| DeepSeek R1 Distill Qwen 14B DeepSeek | Q8_0 | fits | 28.3 GB | 128k | 11tok/sest. | 223 tok/s | chat |
| Muse Glimmer 30B meta-models | Q8_0 | fits | 32.7 GB | 128k | 9tok/sest. | 203 tok/s | – |
| Devstral Small 2507 Mistral AI | Q8_0 | fits | 35.0 GB | 128k | 9tok/sest. | 200 tok/s | – |
| Magistral Small 2506 Mistral AI | Q8_0 | fits | 35.0 GB | 40k | 9tok/sest. | 200 tok/s | – |
| Magistral Small 2507 Mistral AI | Q8_0 | fits | 35.0 GB | 40k | 9tok/sest. | 200 tok/s | – |
| Magistral Small 2509 Mistral AI | Q8_0 | fits | 35.0 GB | 128k | 9tok/sest. | 198 tok/s | – |
| granite 4.2 30b IBM | Q8_0 | fits | 46.7 GB | 125k128k with q8 cache | 6tok/sest. | 148 tok/s | – |
| DeepSeek R1 Distill Llama 70B DeepSeek | Q4_K_M | fits | 61.3 GB | 67k125k with q8 cache | 5tok/sest. | 61 tok/s | – |
| Qwen 3.8 Flash Next Alibaba Qwen | UD-Q2_K_XL | offload | 76.7 GB | – | 3tok/sest. | 92 tok/s | – |
| MiniMax M2.7 MiniMax | UD-Q2_K_XL | offload | 87.3 GB | – | 4tok/sest. | 158 tok/s | chat |
| GLM 4.5V Z.ai | Q4_K_M | offload | 72.4 GB | 9k18k with q8 cache | 5tok/sest. | 123 tok/s | chat |
| GLM 4.6V Z.ai | Q4_K_M | offload | 78.8 GB | – | 4tok/sest. | 117 tok/s | – |
| Kimi Dev 72B Moonshot AI | Q6_K | offload | 81.6 GB | 3k6k with q8 cache | 2tok/sest. | 51 tok/s | – |
| DeepSeek V4 Flash DeepSeek | UD-Q2_K_XL | won't run | 97.2 GB | – | – | – | – |
| GLM 5.3 Flash Z.ai | UD-Q2_K_XL | won't run | 103.7 GB | – | – | – | – |
| DeepSeek R1 DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek R1 0528 DeepSeek | Q4_K_M | won't run | 383.1 GB | – | – | – | – |
| DeepSeek R1 Zero DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek V3 DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek V3 0324 DeepSeek | Q4_K_M | won't run | 382.6 GB | – | – | – | – |
| DeepSeek V3.1 DeepSeek | Q4_K_M | won't run | 383.5 GB | – | – | – | – |
| DeepSeek V3.1 Terminus DeepSeek | Q4_K_M | won't run | 383.5 GB | – | – | – | – |
| DeepSeek V3.2 DeepSeek | Q4_K_M | won't run | 383.5 GB | – | – | – | – |
| DeepSeek V4 Flash 0731 DeepSeek | MXFP4 | won't run | 152.7 GB | – | – | – | – |
| DeepSeek V4 Flash Vision Exp DeepSeek | MXFP4 | won't run | 161.5 GB | – | – | – | – |
| Devstral 2 123B Instruct 2512 Mistral AI | Q4_K_M | won't run | 93.4 GB | – | – | – | – |
| GLM 4.5 Z.ai | Q4_K_M | won't run | 226.3 GB | – | – | – | – |
| GLM 4.6 Z.ai | Q4_K_M | won't run | 225.5 GB | – | – | – | – |
| GLM 4.7 Z.ai | Q4_K_M | won't run | 226.3 GB | – | – | – | – |
| GLM 5 Z.ai | MXFP4 | won't run | 389.5 GB | – | – | – | – |
| GLM 5.1 Z.ai | MXFP4 | won't run | 427.1 GB | – | – | – | – |
| GLM 5.2 Z.ai | UD-Q4_K_M | won't run | 441.0 GB | – | – | – | – |
| GLM 5.3 Z.ai | Q8_0 | won't run | 753.5 GB | – | – | – | – |
| Kimi K2 Moonshot AI | Q4_K_M | won't run | 584.1 GB | – | – | – | – |
| Kimi K2 Instruct 0905 Moonshot AI | Q4_K_M | won't run | 584.5 GB | – | – | – | – |
| Kimi K2 Thinking Moonshot AI | Q4_K_M | won't run | 584.5 GB | – | – | – | – |
| Kimi K2.5 Moonshot AI | Q4_K_M | won't run | 584.5 GB | – | – | – | – |
| MiniMax M2 MiniMax | Q4_K_M | won't run | 146.0 GB | – | – | – | – |
| MiniMax M2.1 MiniMax | Q4_K_M | won't run | 146.0 GB | – | – | – | – |
| MiniMax M2.5 MiniMax | MXFP4 | won't run | 132.4 GB | – | – | – | – |
| MiniMax M3 MiniMax | MXFP4 | won't run | 248.9 GB | – | – | – | – |
| Mistral Medium 3.5 128B Mistral AI | Q4_K_M | won't run | 93.4 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 64k context and generates at about 9 tok/s, an estimate from its memory bandwidth. 70 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 97 GB at 64k 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 64k context. See the best hardware for local AI at every budget.