IntelXe2 (Battlemage), 2x BMG-G21 (Xe2-HPG)

Best AI Models for Intel Arc Pro B60 Dual 48GB (48.0GB)

VRAM:48.0 GB GDDR6·Bandwidth:456.0 GB/s·TDP:400W·MSRP:$1,200

48 GB is two 24 GB GPUs on one board, NOT a unified 48 GB pool — a single model must fit in 24 GB unless you use tensor/pipeline parallelism (vLLM, llama.cpp -ts).

With 48 GB of memory, this is a high-end configuration for local AI. You can comfortably run most open-source LLMs including large 70B parameter models at good quantization levels, making it one of the best setups for serious local AI work.

At this memory tier, nearly every popular open-source model is within reach. You can run Llama 3 70B at Q4_K_M or even Q5_K_M quantization with room to spare, handle coding assistants like DeepSeek Coder 33B at high quality, and easily run any 7B–30B model at full or near-full precision. Context windows remain generous even with larger models, so multi-turn conversations and long-document processing work smoothly.

Runs Well

  • 70B models (Llama 3 70B, Qwen 72B) at Q4–Q5
  • 30B models at Q6–Q8 quality
  • 7B–14B models at full FP16 precision
  • Vision models (LLaVA, CogVLM) without compromise

Challenging

  • Mixture-of-experts models like Mixtral 8x22B at higher quants
  • 120B+ models still require lower quantizations

What LLMs Can Intel Arc Pro B60 Dual 48GB Run?

113 models · 5 good

Showing compatibility for Intel Arc Pro B60 Dual 48GB

LLM models compatible with Intel Arc Pro B60 Dual 48GB — ranked by performance
ModelVRAMGrade
Q4_K_M·11.2 t/s tok/s·33K ctx·FAIR FIT
20.3 GBB57
Qwen1.5 32B32.5B
Q4_K_M·11.2 t/s tok/s·33K ctx·FAIR FIT
20.3 GBB57
Gemma 3 4B IT4.3B
Q4_K_M·80.3 t/s tok/s·EASY RUN
2.8 GBD28
Q4_K_M·12.7 t/s tok/s·8K ctx·FAIR FIT
18.0 GBB52
Qwen2.5 Coder 32B32.8B
Q4_K_M·11.1 t/s tok/s·33K ctx·FAIR FIT
20.5 GBB58
Phi 3 Mini 4k Instruct3.8B
Q4_K_M·67.1 t/s tok/s·4K ctx·EASY RUN
3.4 GBD29
Phi 4 Mini Instruct3.8B
Q4_K_M·79.4 t/s tok/s·131K ctx·EASY RUN
2.9 GBD28
GPT OSS 20B21.5B
Q4_K_M·17.2 t/s tok/s·131K ctx·EASY RUN
13.3 GBC43
Q4_K_M·57.6 t/s tok/s·33K ctx·EASY RUN
4.0 GBD29
Q4_K_M·107.5 t/s tok/s·131K ctx·EASY RUN
2.1 GBD27
Qwen2.5 Coder 3B3.1B
Q4_K_M·102.2 t/s tok/s·33K ctx·EASY RUN
2.2 GBD28
Gemma 3n E2B IT5.4B
Q4_K_M·63.5 t/s tok/s·EASY RUN
3.6 GBD29
Q4_K_M·15.1 t/s tok/s·131K ctx·FAIR FIT
15.1 GBB47
Q4_K_M·225.7 t/s tok/s·2K ctx·EASY RUN
1.0 GBD26
SmolLM3 3B3.1B
Q4_K_M·99.1 t/s tok/s·66K ctx·EASY RUN
2.3 GBD28
Gemma 3 1B IT1000M
Q4_K_M·345.5 t/s tok/s·33K ctx·EASY RUN
0.7 GBD26

Intel Arc Pro B60 Dual 48GB Specifications

Brand
Intel
Architecture
Xe2 (Battlemage), 2x BMG-G21 (Xe2-HPG)
VRAM
48.0 GB GDDR6
Memory Bandwidth
456.0 GB/s
FP16 Performance
197.00 TFLOPS
TDP
400W
Release Date
2025-08-01
MSRP
$1,200

Get Started

Ollama (Recommended)

$curl -fsSL https://ollama.com/install.sh | sh
$ollama run llama3:8b

LM Studio

LM Studio

Download LM Studio, search for a model, and run it with one click.

GPUs to Consider Over Intel Arc Pro B60 Dual 48GB

Similar GPUs and upgrades with more VRAM or higher bandwidth for AI

Frequently Asked Questions

Can Intel Arc Pro B60 Dual 48GB run Mixtral 8x7B Instruct v0.1?

Yes, the Intel Arc Pro B60 Dual 48GB with 48 GB can run Mixtral 8x7B Instruct v0.1, Mixtral 8x7B v0.1, Falcon 40B, and 1334 other models. 11 models run at excellent quality, and 31 at good quality. Check the compatibility table above for the full list with VRAM usage and estimated speed.

Is Intel Arc Pro B60 Dual 48GB good for AI?

The Intel Arc Pro B60 Dual 48GB has 48 GB of GDDR6, making it excellent for running local AI models. It supports 42 models at good quality or better. With 456.0 GB/s memory bandwidth, it delivers solid token generation speeds. This is an enthusiast-grade GPU that handles most popular open-source LLMs.

How many parameters can Intel Arc Pro B60 Dual 48GB handle?

With 48 GB, the Intel Arc Pro B60 Dual 48GB supports models from 3B to 70B+ parameters depending on quantization level. At Q4_K_M (the recommended sweet spot), you can fit roughly 80B parameters. This means 7B models at high quality (Q6/Q8) or 30B+ models at Q4.

What quantization should I use on Intel Arc Pro B60 Dual 48GB?

For the best balance of quality and speed on the Intel Arc Pro B60 Dual 48GB, start with Q4_K_M — it preserves ~85% of the original model quality while keeping VRAM usage reasonable. With 24+ GB, you have the headroom to run 7B models at Q5_K_M or even Q6_K for noticeably better output quality. For larger 30B models, Q4_K_M remains the sweet spot.

How fast is Intel Arc Pro B60 Dual 48GB for AI inference?

With 456.0 GB/s memory bandwidth, the Intel Arc Pro B60 Dual 48GB achieves approximately 51 tokens/sec on a 7B model at Q4_K_M — that's very fast, well above conversational speed. A 14B model runs at ~25 tok/s. Token generation speed scales inversely with model size — smaller models are significantly faster.

tok/s = (456 GB/s ÷ model GB) × efficiency

Smaller models = faster inference. Memory bandwidth is the main bottleneck for token generation speed.

Estimated speed on Intel Arc Pro B60 Dual 48GB

Real-world results typically within ±20%. Speed depends on quantization kernel, batch size, and software stack.

Learn more about tok/s estimation →

What's the best model for Intel Arc Pro B60 Dual 48GB?

The top-rated models for the Intel Arc Pro B60 Dual 48GB are Mixtral 8x7B Instruct v0.1, Mixtral 8x7B v0.1, Falcon 40B. The best choice depends on your use case: coding assistants benefit from code-tuned models, while general chat works well with instruction-tuned models like Llama or Qwen.

What power supply and cooling does Intel Arc Pro B60 Dual 48GB need?

The Intel Arc Pro B60 Dual 48GB has a TDP of 400 W. A good rule of thumb is to provide at least double the GPU's TDP to cover the rest of the system — that means a 850 W PSU or larger. At this power level, a high-airflow case matters: aim for at least two front intake fans and one rear exhaust, with tidy cabling so hot air isn't trapped around the card. LLM inference sustains full GPU load continuously — longer and more consistently than most gaming workloads — so also make sure your CPU cooler can keep up under combined load.

Anything to watch out for with Intel Arc Pro B60 Dual 48GB?

48 GB is two 24 GB GPUs on one board, NOT a unified 48 GB pool — a single model must fit in 24 GB unless you use tensor/pipeline parallelism (vLLM, llama.cpp -ts).