# Intel Arc Pro B60 for local LLMs

> 24GB for about $650 new, among the lowest prices per GB of any current card, with less polished software than CUDA.

The Arc Pro B60 has 24GB of GDDR6 and 456 GB/s of memory bandwidth, which decides how big a model fits and how fast it generates text. It comfortably runs models up to about 35B parameters: the largest in our catalog is Qwen3.6 35B-A3B at Q3_K_M (19GB with 8K context, ~66 tokens/sec). Our top all-round pick for it is Qwen3.8 27B (Q4_K_M, ~15 tokens/sec).

## Key specs

- Memory: 24GB GDDR6
- Memory bandwidth: 456 GB/s
- Architecture: Xe2 (Battlemage) (2025)
- Power: 200W
- Typical price: ~$650 (checked 2026-10)
- Software: SYCL, Vulkan

## Best models for this GPU

- **Best overall (also coding, reasoning, vision):** Qwen3.8 27B at Q4_K_M, ~18.1GB with 8K context, ~15 tokens/sec
- **Runner-up:** Gemma 4 26B A4B at Q5_K_M, ~20.1GB with 8K context, ~43 tokens/sec
- **Fastest good model (also largest that fits):** Qwen3.6 35B-A3B at Q3_K_M, ~19.2GB with 8K context, ~66 tokens/sec

## Compatibility (best quantization that fits, 8K context)

| Model | Params | Quant | Memory | Speed | Verdict |
| --- | --- | --- | --- | --- | --- |
| Gemma 4 E4B | 8B | Q8_0 | 10.5GB | ~25 tok/s | Runs well |
| Qwen3.5 9B | 9B | Q8_0 | 12.0GB | ~22 tok/s | Runs well |
| Phi-4 | 14.7B | Q8_0 | 18.3GB | ~16 tok/s | Runs well |
| gpt-oss-20b | 20.9B (3.6B active) | MXFP4 | 15.0GB | ~48 tok/s | Runs well |
| Gemma 4 26B A4B | 26B (3.8B active) | Q5_K_M | 20.1GB | ~43 tok/s | Runs well |
| Qwen3.8 27B | 27B | Q4_K_M | 18.1GB | ~15 tok/s | Runs well |
| Gemma 4 31B | 31B | Q4_K_M | 22.5GB | ~12 tok/s | Fits, tight |
| Qwen3.6 35B-A3B | 35B (3B active) | Q3_K_M | 19.2GB | ~66 tok/s | Runs well |
| GLM-4.5-Air | 106B (12B active) | Q4_K_M | 68.3GB | ~7.6 tok/s | Partial offload |
| Llama 4 Scout | 109B (17B active) | Q4_K_M | 69.5GB | ~5.4 tok/s | Partial offload |
| gpt-oss-120b | 117B (5.1B active) | MXFP4 | 68.3GB | ~18 tok/s | Partial offload |
| Qwen3.5 122B-A10B | 122B (10B active) | - | - | - | Won't fit |
| DeepSeek V4 Flash | 284B (13B active) | - | - | - | Won't fit |
| GLM-5.3-Flash | 320B (18B active) | - | - | - | Won't fit |
| GLM-5.3 | 744B (40B active) | - | - | - | Won't fit |

## Pros
- 24GB for about $650 new
- Low 120 to 200W power
- Blower versions stack in multi-GPU builds

## Cons
- 456 GB/s is slow for 24GB
- Software support trails CUDA
- Dual-GPU boards need bifurcation support

Full page: https://llamabuilds.ai/gpus/arc-pro-b60 · Best models: https://llamabuilds.ai/gpus/arc-pro-b60/best-models

Sources: [GPU Poet Arc Pro B60 specs and pricing](https://gpupoet.com/gpu/learn/card/intel-arc-pro-b60), [GPUvec Arc Pro B60 specifications](https://gpuvec.com/gpus/arc-pro-b60)

---
Source: https://llamabuilds.ai/gpus/arc-pro-b60 · Updated October 14, 2026 · Llama Builds. Speeds marked ~ are estimates from our bandwidth model (https://llamabuilds.ai/methodology); measured results are labeled as such.