HARDWARE MATCH

What can your GPU run?

Get a practical shortlist based on available VRAM, task and license preference.

SHORTLIST

Models estimated to fit 24 GB

Memory estimates are directional, not benchmarks. Context length, batch size, runtime and quantization affect actual use.
sentence-similarity

sentence-transformers/all-MiniLM-L6-v2

sentence-transformers/all-MiniLM-L6-v2 is a sentence similarity model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.

↓ 218,138,134♡ 6,339
Unknown4 GB+ VRAMapache-2.0
Deployment details →
text-ranking

cross-encoder/ms-marco-MiniLM-L6-v2

cross-encoder/ms-marco-MiniLM-L6-v2 is a text ranking model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 78,821,870♡ 414
Unknown8 GB+ VRAMapache-2.0
Deployment details →
feature-extraction

BAAI/bge-small-en-v1.5

BAAI/bge-small-en-v1.5 is a feature extraction model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.

↓ 59,413,346♡ 643
Unknown4 GB+ VRAMmit
Deployment details →
general AI

google/electra-base-discriminator

google/electra-base-discriminator is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 43,209,529♡ 216
Unknown8 GB+ VRAMapache-2.0
Deployment details →
fill-mask

google-bert/bert-base-uncased

google-bert/bert-base-uncased is a fill mask model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 34,423,988♡ 3,430
Unknown8 GB+ VRAMapache-2.0
Deployment details →
sentence-similarity

BAAI/bge-m3

BAAI/bge-m3 is a sentence similarity model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.

↓ 32,530,460♡ 3,891
Unknown4 GB+ VRAMmit
Deployment details →
text-generation

Qwen/Qwen3-0.6B

Qwen/Qwen3-0.6B is a text generation model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.

↓ 30,452,693♡ 1,813
600M4 GB+ VRAMapache-2.0
Deployment details →
general AI

Comfy-Org/MiniMax-H3

Comfy-Org/MiniMax-H3 is a AI workload model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 24,139,135♡ 2,272
Unknown8 GB+ VRAMother
Deployment details →
translation

google-t5/t5-small

google-t5/t5-small is a translation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 23,798,595♡ 682
Unknown8 GB+ VRAMapache-2.0
Deployment details →
image-classification

timm/mobilenetv3_small_100.lamb_in1k

timm/mobilenetv3_small_100.lamb_in1k is a image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 21,526,633♡ 151
Unknown8 GB+ VRAMapache-2.0
Deployment details →
time-series-forecasting

amazon/chronos-2

amazon/chronos-2 is a time series forecasting model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 18,826,021♡ 535
Unknown8 GB+ VRAMapache-2.0
Deployment details →
zero-shot-image-classification

openai/clip-vit-base-patch32

openai/clip-vit-base-patch32 is a zero shot image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 18,599,695♡ 1,615
Unknown8 GB+ VRAMLicense unknown
Deployment details →
sentence-similarity

sentence-transformers/all-mpnet-base-v2

sentence-transformers/all-mpnet-base-v2 is a sentence similarity model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.

↓ 18,064,033♡ 1,395
Unknown4 GB+ VRAMapache-2.0
Deployment details →
text-generation

openai-community/gpt2

openai-community/gpt2 is a text generation model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 16,001,636♡ 4,251
Unknown8 GB+ VRAMmit
Deployment details →
text-classification

BAAI/bge-reranker-v2-m3

BAAI/bge-reranker-v2-m3 is a text classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 15,915,292♡ 1,258
Unknown8 GB+ VRAMapache-2.0
Deployment details →
automatic-speech-recognition

jonatasgrosman/wav2vec2-large-xlsr-53-japanese

jonatasgrosman/wav2vec2-large-xlsr-53-japanese is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 15,587,437♡ 107
Unknown8 GB+ VRAMapache-2.0
Deployment details →
sentence-similarity

nomic-ai/nomic-embed-text-v1.5

nomic-ai/nomic-embed-text-v1.5 is a sentence similarity model indexed for deployment research. Estimated minimum GPU memory is 4 GB. It is publicly listed on Hugging Face.

↓ 13,143,085♡ 977
Unknown4 GB+ VRAMapache-2.0
Deployment details →
image-classification

google/vit-base-patch16-224

google/vit-base-patch16-224 is a image classification model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 12,778,516♡ 1,037
Unknown8 GB+ VRAMapache-2.0
Deployment details →
text-generation

Qwen/Qwen3-4B

Qwen/Qwen3-4B is a text generation model indexed for deployment research. Estimated minimum GPU memory is 12 GB. It is publicly listed on Hugging Face.

↓ 12,585,505♡ 759
4.0B12 GB+ VRAMapache-2.0
Deployment details →
object-detection

mudler/locate-anything.cpp-gguf

mudler/locate-anything.cpp-gguf is a object detection model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 12,336,750♡ 52
Unknown8 GB+ VRAMother
Deployment details →
automatic-speech-recognition

argmaxinc/whisperkit-coreml

argmaxinc/whisperkit-coreml is a automatic speech recognition model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 11,887,526♡ 249
Unknown8 GB+ VRAMmit
Deployment details →
fill-mask

FacebookAI/xlm-roberta-base

FacebookAI/xlm-roberta-base is a fill mask model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 10,798,447♡ 958
Unknown8 GB+ VRAMmit
Deployment details →
text-to-speech

hexgrad/Kokoro-82M

hexgrad/Kokoro-82M is a text to speech model indexed for deployment research. Estimated minimum GPU memory is 8 GB. It is publicly listed on Hugging Face.

↓ 10,546,822♡ 7,249
Unknown8 GB+ VRAMapache-2.0
Deployment details →