Efficient Inference for Large Reasoning Models: A Survey
Paper
•
2503.23077
•
Published
•
45
San
san122
·
AI & ML interests
Large Language Models, Quantization, Vision, Multimodality, Diffusion models
Recent Activity
commented on
a paper
9 days ago
Scaling Language-Free Visual Representation Learning
upvoted
a
paper
11 days ago
Efficient Inference for Large Reasoning Models: A Survey
reacted
to
ImranzamanML's
post
with 👍
6 months ago
Here is how we can calculate the size of any LLM model:
Each parameter in LLM models is typically stored as a floating-point number. The size of each parameter in bytes depends on the precision.
32-bit precision: Each parameter takes 4 bytes.
16-bit precision: Each parameter takes 2 bytes
To calculate the total memory usage of the model:
Memory usage (in bytes) = No. of Parameters × Size of Each Parameter
For example:
32-bit Precision (FP32)
In 32-bit floating-point precision, each parameter takes 4 bytes.
Memory usage in bytes = 1 billion parameters × 4 bytes
1,000,000,000 × 4 = 4,000,000,000 bytes
In gigabytes: ≈ 3.73 GB
16-bit Precision (FP16)
In 16-bit floating-point precision, each parameter takes 2 bytes.
Memory usage in bytes = 1 billion parameters × 2 bytes
1,000,000,000 × 2 = 2,000,000,000 bytes
In gigabytes: ≈ 1.86 GB
It depends on whether you use 32-bit or 16-bit precision, a model with 1 billion parameters would use approximately 3.73 GB or 1.86 GB of memory, respectively.
Organizations
None yet