Question 1

What AI models can run on A10G?

Accepted Answer

The A10G (24 GB VRAM) can run models including Llama-2-7b-chat, Llama-3.2-1B-Instruct-SpinQuant_INT4_EO8, FastContext-1.0-4B-RL, Llama-3.2-1B-Instruct-QLORA_INT4_EO8, HARC-Llama-3.1-8B-Instruct and more — 10 compatible models indexed so far. Compatible models are determined by whether the model's memory footprint fits within the GPU's 24 GB VRAM, potentially using quantization (Q8, Q6, or Q4) to reduce memory usage.

Question 2

What is the cheapest cloud option for A10G?

Accepted Answer

The cheapest on-demand option for the A10G is Amazon Web Services at $1.01/hr (g5.xlarge). Spot/preemptible pricing is available at $0.84/hr. We track pricing across 75 providers to help you find the best deal.

Question 3

Is A10G good for fine-tuning?

Accepted Answer

The A10G can handle fine-tuning with some constraints. With 24 GB of VRAM, it's suitable for LoRA/QLoRA fine-tuning of models up to ~7B parameters. Full fine-tuning is limited to smaller models (~1-3B parameters). Techniques like gradient checkpointing and mixed precision help maximize what fits.

Question 4

How much VRAM does A10G have?

Accepted Answer

The A10G has 24 GB of VRAM (GDDR6). It also offers 600 GB/s memory bandwidth, 35.6 TFLOPS of FP16 compute.

Question 5

What quantization formats work on A10G?

Accepted Answer

The A10G supports the following quantization formats: FP16 (full precision), Q8 (8-bit), Q6 (6-bit), Q4 (4-bit). FP16 works for models up to ~7B parameters. Q4 quantization lets models up to ~81B parameters (by VRAM estimate) fit on the A10G.

A10G

Specifications

Cloud pricing

Compatible models

Compare this GPU

Frequently asked questions

VRAM	24 GB
Memory type	GDDR6
Bandwidth	600 GB/s
FP16 TFLOPS	35.6
FP8 support	No