Question 1

How much VRAM does open-instruct-gpt4-alpaca-13b need?

Accepted Answer

open-instruct-gpt4-alpaca-13b (13B) requires approximately 29.09274673461914 GB of VRAM at full precision (FP16), 14.5 GB at 8-bit quantization (Q8), and 7.3 GB at 4-bit quantization (Q4). The actual VRAM usage may be slightly higher due to KV cache and runtime overhead.

Question 2

What GPUs can run open-instruct-gpt4-alpaca-13b?

Accepted Answer

We have 10 compatible GPUs indexed for open-instruct-gpt4-alpaca-13b, including A40, L40S, L40, A100 40GB, RTX A6000 and 5 more. Compatibility is determined by whether the GPU's VRAM can fit the model's memory footprint, potentially using quantization to reduce memory usage.

Question 3

What is the cheapest GPU to run open-instruct-gpt4-alpaca-13b?

Accepted Answer

The cheapest GPU to run open-instruct-gpt4-alpaca-13b in the cloud is the A40 at $0.44/hr. Other affordable options include L40S ($0.60/hr) and L40 ($0.82/hr). Prices reflect the lowest on-demand rate across cloud providers.

Question 4

Can open-instruct-gpt4-alpaca-13b run on consumer hardware?

Accepted Answer

Yes, open-instruct-gpt4-alpaca-13b can run on consumer GPUs like the RTX A6000 (48 GB VRAM) at full precision (FP16).

Question 5

What quantization options are available for open-instruct-gpt4-alpaca-13b?

Accepted Answer

open-instruct-gpt4-alpaca-13b supports the following quantization levels: FP16 (full precision): ~29.09274673461914 GB, Q8 (8-bit): ~14.5 GB, Q6 (6-bit): ~10.9 GB, Q4 (4-bit): ~7.3 GB. Lower quantization reduces VRAM usage at the cost of some quality loss. Q8 offers a good balance between quality and memory savings, while Q4 provides maximum compression.

GPU	VRAM	Best Quant	From	Rent
A40	48 GB	FP16	$0.44/hr	Rent
L40S	48 GB	FP16	$0.60/hr	Rent
L40	48 GB	FP16	$0.82/hr	Rent
A100 40GB	40 GB	FP16	$0.93/hr	Rent
RTX A6000	48 GB	FP16	$1.09/hr
A100 80GB PCIe	80 GB	FP16	$1.39/hr	Rent
A100 80GB	80 GB	FP16	$1.39/hr	Rent
H100 MEGA	80 GB	FP16	$1.80/hr	Rent
H100 SXM	80 GB	FP16	$1.80/hr	Rent
H100 NVL	94 GB	FP16	$1.80/hr	Rent

open-instruct-gpt4-alpaca-13b

VRAM Requirements

Compatible GPUs

open-instruct-gpt4-alpaca-13b FAQ

VRAM requirements for open-instruct-gpt4-alpaca-13b at different quantization levels
Quantization	VRAM Required
FP16	29.1 GB
Q8	14.5 GB
Q6	10.9 GB
Q4	7.3 GB