Question 1

What AI models can run on Arc B580?

Accepted Answer

The Arc B580 (12 GB VRAM) can run models including paligemma-3b-ft-vizwizvqa-448-jax, intent-aware-lfqa-qwen3-4b-intent-implicit, intent-aware-lfqa-qwen3-4b-baseline, Llama-3.2-3B-Instruct-QLORA_INT4_EO8, Llama-3.2-3B-Instruct-SpinQuant_INT4_EO8 and more — 10 compatible models indexed so far. Compatible models are determined by whether the model's memory footprint fits within the GPU's 12 GB VRAM, potentially using quantization (Q8, Q6, or Q4) to reduce memory usage.

Question 2

What is the cheapest cloud option for Arc B580?

Accepted Answer

We don't currently have cloud pricing data for the Arc B580. This GPU may not be widely available from major cloud providers, or pricing data hasn't been synced yet.

Question 3

Is Arc B580 good for fine-tuning?

Accepted Answer

The Arc B580 has limited capacity for fine-tuning with only 12 GB of VRAM. It can handle QLoRA fine-tuning of small models (up to ~3B parameters) but is not recommended for larger training workloads. Consider a GPU with more VRAM for serious fine-tuning.

Question 4

How much VRAM does Arc B580 have?

Accepted Answer

The Arc B580 has 12 GB of VRAM (GDDR6). It also offers 456 GB/s memory bandwidth, 27.3 TFLOPS of FP16 compute.

Question 5

What quantization formats work on Arc B580?

Accepted Answer

The Arc B580 supports the following quantization formats: Q8 (8-bit), Q6 (6-bit), Q4 (4-bit). Q4 quantization can fit models requiring up to ~48 GB at FP16 into 12 GB.

Arc B580

Specifications

Cloud pricing

Compatible models

Compare this GPU

Frequently asked questions

VRAM	12 GB
Memory type	GDDR6
Bandwidth	456 GB/s
FP16 TFLOPS	27.3
FP8 support	No