IntelXe2 (Battlemage), BMG-G21

Best AI Models for Intel Arc Pro B60 (24.0GB)

VRAM:24.0 GB GDDR6·Bandwidth:456.0 GB/s·TDP:200W·MSRP:$599

Workstation Battlemage card; runs LLMs via IPEX-LLM / llama.cpp (Vulkan/SYCL). 24 GB at a low price, but the software stack is less mature than CUDA/ROCm.

24 GB is the enthusiast tier for running AI models locally. It comfortably handles 7B–13B models at high quality and opens the door to larger 30B models at moderate quantization.

This is one of the most popular memory tiers for local AI, found in GPUs like the RTX 4090 and RTX 3090. You can run Llama 3 8B, Mistral 7B, and Qwen 2.5 7B at Q5_K_M or Q6_K quality with fast token generation and generous context windows. Larger 14B models like DeepSeek R1 Distill fit comfortably at Q4_K_M. For even bigger models, 30B class runs at Q2–Q3, but 70B models are generally too heavy for single-GPU inference at this tier.

Runs Well

  • 7B models (Llama 3 8B, Mistral 7B) at Q5–Q8 quality
  • 13B–14B models at Q4–Q5 quality
  • Small models (3B–4B) at FP16 precision
  • Multimodal models like LLaVA 7B

Challenging

  • 30B models only at Q2–Q3 quantization
  • 70B models do not fit in VRAM
  • Large context windows with 14B+ models

What LLMs Can Intel Arc Pro B60 Run?

105 models · 7 excellent · 15 good

Showing compatibility for Intel Arc Pro B60

LLM models compatible with Intel Arc Pro B60 — ranked by performance
ModelVRAMGrade
Gemma 3n E2B IT5.4B
Q4_K_M·63.5 t/s tok/s·EASY RUN
3.6 GBC33
Phi 3 Mini 4k Instruct3.8B
Q4_K_M·67.1 t/s tok/s·4K ctx·EASY RUN
3.4 GBC32
Phi 4 Mini Instruct3.8B
Q4_K_M·79.4 t/s tok/s·131K ctx·EASY RUN
2.9 GBC31
Q4_K_M·42.1 t/s tok/s·16K ctx·EASY RUN
5.4 GBC38
Qwen 14B14.2B
Q4_K_M·24.4 t/s tok/s·8K ctx·FAIR FIT
9.3 GBB54
Hermes 3 Llama 3.1 8B8.0B
Q4_K_M·42.3 t/s tok/s·131K ctx·EASY RUN
5.4 GBC37
Qwen 14B Chat14.2B
Q4_K_M·24.4 t/s tok/s·8K ctx·FAIR FIT
9.3 GBB54
Q4_K_M·39.7 t/s tok/s·66K ctx·EASY RUN
5.8 GBC39
Q4_K_M·107.5 t/s tok/s·131K ctx·EASY RUN
2.1 GBC30
Qwen1.5 7B7.7B
Q4_K_M·37.9 t/s tok/s·33K ctx·EASY RUN
6.0 GBC40
Q4_K_M·278.0 t/s tok/s·131K ctx·EASY RUN
0.8 GBD27
Yi 34B Chat34.4B
Q4_K_M·10.6 t/s tok/s·4K ctx·FAIR FIT
21.4 GBB56
Phi 22.8B
Q4_K_M·86.4 t/s tok/s·2K ctx·EASY RUN
2.6 GBC31
Qwen2.5 Coder 3B3.1B
Q4_K_M·102.2 t/s tok/s·33K ctx·EASY RUN
2.2 GBC30
Yi 6B Chat6.1B
Q4_K_M·56.0 t/s tok/s·4K ctx·EASY RUN
4.1 GBC34
SmolLM3 3B3.1B
Q4_K_M·99.1 t/s tok/s·66K ctx·EASY RUN
2.3 GBC30

Intel Arc Pro B60 Specifications

Brand
Intel
Architecture
Xe2 (Battlemage), BMG-G21
VRAM
24.0 GB GDDR6
Memory Bandwidth
456.0 GB/s
FP16 Performance
98.50 TFLOPS
TDP
200W
Release Date
2025-09-19
MSRP
$599

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

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

Frequently Asked Questions

Can Intel Arc Pro B60 run Gemma 3 27B IT?

Yes, the Intel Arc Pro B60 with 24 GB can run Gemma 3 27B IT, Qwen3.6 27B, Gemma 4 26B A4B IT, and 1264 other models. 69 models run at excellent quality, and 153 at good quality. Check the compatibility table above for the full list with VRAM usage and estimated speed.

Is Intel Arc Pro B60 good for AI?

The Intel Arc Pro B60 has 24 GB of GDDR6, making it excellent for running local AI models. It supports 222 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 handle?

With 24 GB, the Intel Arc Pro B60 supports models from 3B to 30B parameters depending on quantization level. At Q4_K_M (the recommended sweet spot), you can fit roughly 40B 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?

For the best balance of quality and speed on the Intel Arc Pro B60, 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 for AI inference?

With 456.0 GB/s memory bandwidth, the Intel Arc Pro B60 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

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?

The top-rated models for the Intel Arc Pro B60 are Gemma 3 27B IT, Qwen3.6 27B, Gemma 4 26B A4B IT. 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 need?

The Intel Arc Pro B60 has a TDP of 200 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 550 W PSU or larger. A mid-tower case with one intake and one rear exhaust is usually sufficient. Keep dust filters clean, as sustained inference generates continuous heat rather than the brief spikes typical of gaming.

Anything to watch out for with Intel Arc Pro B60?

Workstation Battlemage card; runs LLMs via IPEX-LLM / llama.cpp (Vulkan/SYCL). 24 GB at a low price, but the software stack is less mature than CUDA/ROCm.