The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
SAVRN Model Hub · Models by Task
Feature Extraction Models
77 open-weight feature extraction models in the SAVRN Model Hub, with Beijing Academy of Artificial Intelligence, Qwen and Jina AI publishing the most.
77Models
61Publishers
12M to 7.6BParameter range
4Licenses
SAVRN's Take
Every retrieval pipeline we stand up starts with one of these. A feature extraction model turns a passage of text, or in one case audio, into a fixed-length vector a database can compare against millions of others, which is how semantic search finds the right chunk. The Beijing Academy of Artificial Intelligence leads the 77 entries with 8 models, and its bge-small-en-v1.5 pulls 64,516,396 downloads a month, more than five times the 11,607,634 of bge-large-en-v1.5. Qwen and Jina AI follow with 3 each.
Hardware is the easy part. bge-small-en-v1.5 needs 0.1 GB at 16-bit, and even Qwen3-Embedding-8B at 7.6B parameters fits in 18.2 GB, or 4.5 GB at 4-bit. The cheapest Index host for all of them is a single MI300X at $1.85 an hour, so the question in our facilities is how much of a card to give the embedding service beside the generation model it feeds. Context length is where the choices separate: the BGE English models stop at 512 tokens, which means chunking every document, while granite-embedding-small-english-r2 takes 8,192 in 48M parameters and the Qwen3 embedding models take 32,768 at 0.6B and 40,960 at 8B.
Licensing rarely blocks a deployment. 54 of the 77 are MIT and 15 are Apache-2.0, both fine for commercial use. Seven state no license and one is cc-by-nc-4.0, so check those eight first. Then weigh vector width: the Granite model emits 384 dimensions, multilingual-e5-large 1024, and the wider vector costs more to store per chunk. Weigh language too: bge v1.5 comes in English and Chinese editions, and multilingual-e5-large covers 100 languages.
Most Downloaded
| Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit |
|---|---|---|---|---|---|
| bge-small-en-v1.5 | Beijing Academy of Artificial Intelligence | 33M | mit | 64.5M | 1x MI300X, $1.85/hr |
| bge-large-en-v1.5 | Beijing Academy of Artificial Intelligence | 335M | mit | 11.6M | 1x MI300X, $1.85/hr |
| bge-base-en-v1.5 | Beijing Academy of Artificial Intelligence | 109M | mit | 10.5M | 1x MI300X, $1.85/hr |
| Qwen3-Embedding-0.6B | Qwen | 596M | apache-2.0 | 8.5M | 1x MI300X, $1.85/hr |
| multilingual-e5-large | Liang Wang | 560M | mit | 7.1M | 1x MI300X, $1.85/hr |
| granite-embedding-small-english-r2 | IBM Granite | 48M | apache-2.0 | 6.4M | 1x MI300X, $1.85/hr |
| bge-small-zh-v1.5 | Beijing Academy of Artificial Intelligence | 24M | mit | 5.1M | 1x MI300X, $1.85/hr |
| all-MiniLM-L6-v2 | Joshua | — | apache-2.0 | 2.9M | — |
| bge-reranker-large | Beijing Academy of Artificial Intelligence | 560M | mit | 2.8M | 1x MI300X, $1.85/hr |
| Qwen3-Embedding-8B | Qwen | 7.6B | apache-2.0 | 2.6M | 1x MI300X, $1.85/hr |
Licenses
| License | Models | Commercial use |
|---|---|---|
| mit | 54 | Yes |
| apache-2.0 | 15 | Yes |
| not stated | 7 | Not stated |
| cc-by-nc-4.0 | 1 | Not without separate permission |
Who Publishes Them
| Publisher | Models |
|---|---|
| Beijing Academy of Artificial Intelligence | 8 |
| Qwen | 3 |
| Jina AI | 3 |
| Joshua | 2 |
| Unsloth Backup Account | 2 |
| Microsoft | 2 |
All 77 Models, Page 2 of 2
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models. Compared to the previous version, the upgraded model shows significant improvements in handling complex reasoning tasks. For instance, in the AIME 2025 test, the model’s accuracy has…
Vela Omni Mini maps text, images, and speech into a shared embedding space for multimodal search, routing, and use a 0–100 scale; higher is better. All applicable models use the same examples and retrieval pools. N/A denotes a modality the text-only model does not support. Bold Vela scores improve on multi-modal-embed-large. Macro-F1 gives equal weight to every intent class (77 for Banking77 and 60 for MASSIVE), complementing the query-weighted accuracy; undefined class F1 is zero. Text evaluation uses fixed class prototypes: 3,080 Banking77 and 2,972 MASSIVE English queries. Vela Omni is adapted using training examples and intent labels from these two datasets; comparison models are…
Vela Omni Nano maps text, images, and speech into a shared embedding space for multimodal search, routing, and use a 0–100 scale; higher is better. All applicable models use the same examples and retrieval pools. N/A denotes a modality the text-only model does not support. Bold Vela scores improve on multi-modal-embed-small. Macro-F1 gives equal weight to every intent class (77 for Banking77 and 60 for MASSIVE), complementing the query-weighted accuracy; undefined class F1 is zero. Text evaluation uses fixed class prototypes: 3,080 Banking77 and 2,972 MASSIVE English queries. Vela Omni is adapted using training examples and intent labels from these two datasets; comparison models are…
Questions
Which Feature extraction models are most downloaded?
By monthly downloads reported by the Hugging Face Hub: .