Model catalog

Pick a category, pick a model, and deploy in one click.

Embeddings

Semantic search and retrieval

3 models

BGE-M3
llama.cpp · Q8_0
- M4 Pro · 24 GB unifiedBest value
  Q8_0 · needs 4 GB · est. 258–366 tok/s
  Deployable now · $0.12/h
- RTX 4090 · 24 GBFastest
  Q8_0 · needs 4 GB · est. 953–1351 tok/s
  Unavailable
- RTX 3080 Ti · 12 GB
  Q8_0 · needs 4 GB · est. 862–1222 tok/s
  Unavailable
- M1 · 16 GB unified
  Q8_0 · needs 4 GB
  Unavailable
16 more
nomic-embed-text v1.5
llama.cpp · Q8_0
- M4 Pro · 24 GB unifiedBest value
  Q8_0 · needs 4 GB · est. 1120–1588 tok/s
  Deployable now · $0.12/h
- RTX 4090 · 24 GBFastest
  Q8_0 · needs 4 GB · est. 4138–5863 tok/s
  Unavailable
- RTX 3080 Ti · 12 GB
  Q8_0 · needs 4 GB · est. 3744–5305 tok/s
  Unavailable
- M1 · 16 GB unified
  Q8_0 · needs 4 GB
  Unavailable
16 more
Qwen3 Embedding 0.6B
0.6B
llama.cpp · Q8_0
- M4 Pro · 24 GB unifiedBest value
  Q8_0, Q4, FP16 · needs 4 GB · est. 256–364 tok/s
  Deployable now · $0.12/h
- RTX 4090 · 24 GBFastest
  Q8_0, Q4, FP16 · needs 4 GB · est. 946–1341 tok/s
  Unavailable
- RTX 3080 Ti · 12 GB
  Q8_0, Q4, FP16 · needs 4 GB · est. 856–1213 tok/s
  Unavailable
- M1 · 16 GB unified
  Q8_0, Q4, FP16 · needs 4 GB
  Unavailable
16 more

Not sure what runs on your machine? See what fits.