sam2.1-hiera-tiny
facebookapache-2.0vision

sam2.1-hiera-tiny

Updated Nov 21, 2026
Parameters
40M
License
apache-2.0
Updated
Nov 21, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at FP16
4 of 4 quantizations fit sam2.1-hiera-tiny with real runtime overhead.
Q4_K_M
1 GB
Q5_K_M
1 GB
Q8_0
1 GB
FP16
1 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve facebook/sam2.1-hiera-tiny

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

sam2.1-hiera-tiny is an open-weight image segmentation model published by facebook on Hugging Face in September 2024, with 40M parameters under the apache-2.0 license.

Among the 23 image segmentation models in this directory it ranks 12th by monthly Hugging Face downloads, and 19 of the others are larger.

HardwareLink to this section

Unquantized FP16 weights take about 1 GB; 8-bit brings that to ~1 GB and 4-bit (Q4_K_M) to ~1 GB, before activations and any context or image buffers. At this size it runs on almost any recent GPU, on Apple Silicon, and usable on a modern CPU. Check exact numbers for your card with the VRAM calculator.

Similar image segmentation modelsLink to this section

PopularityLink to this section

sam2.1-hiera-tiny was downloaded 163,502 times on Hugging Face in the last month (1,007,542 all-time) and has 35 likes.

Run it locallyLink to this section

Weights and usage instructions are on the facebook/sam2.1-hiera-tiny model card; it loads with Hugging Face Transformers.

Local runtimes that fit this model:

  • comfyui - node-based workflows, the usual way to run diffusion models locally
  • invokeai - a canvas UI for image generation and editing
  • transformers - the reference Python library most model cards target

PaperLink to this section

Frequently asked

Quick answers to common questions

How much VRAM does sam2.1-hiera-tiny need?

sam2.1-hiera-tiny with 40M parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is sam2.1-hiera-tiny better than other facebook models?

sam2.1-hiera-tiny has 40M parameters - a strong choice for image-segmentation.

What license is sam2.1-hiera-tiny under?

sam2.1-hiera-tiny is released under the apache-2.0 license, making it suitable for most commercial and personal projects.

What hardware runs sam2.1-hiera-tiny well?

With 40M parameters, sam2.1-hiera-tiny is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs. Check our hardware directory for specific recommendations.

What is the best quantization for sam2.1-hiera-tiny?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with sam2.1-hiera-tiny?

sam2.1-hiera-tiny competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec