Best AI Models for Intel Arc Pro B60 (24.0GB)
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?
123 models · 22 excellent · 47 good
Showing compatibility for Intel Arc Pro B60
| Model | Quant | VRAM | Speed | Context | Status | Grade |
|---|---|---|---|---|---|---|
Q4_K_M·13.1 t/s tok/s·262K ctx·DECENT | Q4_K_M | 17.4 GB | 13.1 t/s | 262K | DECENT | B52 |
Q4_K_M·12.6 t/s tok/s·131K ctx·DECENT | Q4_K_M | 18.1 GB | 12.6 t/s | 131K | DECENT | B51 |
Q4_K_M·13.8 t/s tok/s·262K ctx·DECENT | Q4_K_M | 16.6 GB | 13.8 t/s | 262K | DECENT | B53 |
Q4_K_M·12.2 t/s tok/s·262K ctx·DECENT | Q4_K_M | 18.7 GB | 12.2 t/s | 262K | DECENT | B51 |
Q4_K_M·12.2 t/s tok/s·262K ctx·DECENT | Q4_K_M | 18.7 GB | 12.2 t/s | 262K | DECENT | B51 |
Q4_K_M·12.7 t/s tok/s·8K ctx·DECENT | Q4_K_M | 18.0 GB | 12.7 t/s | 8K | DECENT | B51 |
Q4_K_M·14.1 t/s tok/s·262K ctx·DECENT | Q4_K_M | 16.1 GB | 14.1 t/s | 262K | DECENT | B53 |
Q4_K_M·12.4 t/s tok/s·262K ctx·DECENT | Q4_K_M | 18.4 GB | 12.4 t/s | 262K | DECENT | B51 |
Q4_K_M·12.2 t/s tok/s·262K ctx·DECENT | Q4_K_M | 18.7 GB | 12.2 t/s | 262K | DECENT | B51 |
Q4_K_M·12.2 t/s tok/s·500K ctx·DECENT | Q4_K_M | 18.7 GB | 12.2 t/s | 500K | DECENT | B51 |
Q4_K_M·15.1 t/s tok/s·131K ctx·DECENT | Q4_K_M | 15.1 GB | 15.1 t/s | 131K | DECENT | B55 |
Q4_K_M·13.5 t/s tok/s·262K ctx·DECENT | Q4_K_M | 16.9 GB | 13.5 t/s | 262K | DECENT | B53 |
BF16·14.8 t/s tok/s·4K ctx·DECENT | BF16 | 15.4 GB | 14.8 t/s | 4K | DECENT | B55 |
BF16·14.9 t/s tok/s·8K ctx·DECENT | BF16 | 15.3 GB | 14.9 t/s | 8K | DECENT | B55 |
Q4_K_M·15.3 t/s tok/s·33K ctx·DECENT | Q4_K_M | 14.9 GB | 15.3 t/s | 33K | DECENT | B55 |
Q4_K_M·17.2 t/s tok/s·131K ctx·DECENT | Q4_K_M | 13.3 GB | 17.2 t/s | 131K | DECENT | B57 |
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
Prompt Processing
Estimated for Qwen1.5 MoE A2.7B, the compute-bound phase that reads your prompt before the first reply token appears.
Short chat
156 ms
512 tok prompt
Long chat
1.2 s
4,096 tok prompt
Document / codebase
10.0 s
32,768 tok prompt
Prefill is compute-bound and a different number from the decode tok/s shown elsewhere on this page — how prompt processing works →
Efficiency & Value
Based on Qwen1.5 MoE A2.7B at ~24.5 tok/s decode.
Tokens per watt
Higher is better.
$ per tok/s (MSRP)
MSRP-based, not street price. Lower is better.
Performance figures are estimates calibrated as of 2026-07-30 — see calibration basis →
GPUs to Consider Over Intel Arc Pro B60
Similar GPUs and upgrades with more VRAM or higher bandwidth for AI
NVIDIA GeForce RTX 5090
NVIDIA · Blackwell
NVIDIA GeForce RTX 3090 Ti
NVIDIA · Ampere
NVIDIA GeForce RTX 4090
NVIDIA · Ada Lovelace
AMD Radeon RX 7900 XTX
AMD · RDNA 3
NVIDIA GeForce RTX 3090
NVIDIA · Ampere
NVIDIA GeForce RTX 5090 Laptop GPU
NVIDIA · Blackwell
Frequently Asked Questions
- Can Intel Arc Pro B60 run Qwen3.6 27B?
Yes, the Intel Arc Pro B60 with 24 GB can run Qwen3.6 27B, Gemma 3 27B IT, Gemma 4 26B A4B IT, and 1520 other models. 527 models run at excellent quality, and 551 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 1078 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
~13 tok/s~13 tok/s~14 tok/s~12 tok/sReal-world results typically within ±20%. Speed depends on quantization kernel, batch size, and software stack.
- What's the best model for Intel Arc Pro B60?
The top-rated models for the Intel Arc Pro B60 are Qwen3.6 27B, Gemma 3 27B IT, 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.