Giga Embeddings Instruct measured on 17 of 261 Embeddings benchmarks17
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
59.7MTEB English v2
Sep 2025released
2,048Dimensions
4K tokensMax input
en, ruLanguages
Rankingconfiguration unstated?
Full ranking →···
31ICT TIME And Querit Embedding v156.332Giga Embeddings Instruct56.233Tarka Embedding 350M v155.7Strong at
Alternatives?
ModelScoreCostPriceWhat changes
BetterQwen 3 Embedding 8BunstatedOpen+4%—$0.01Languages: not verified+1cOpenF2LLM 4Bunstated+22%——Languages: loses ru+1
BetterGemini Embedding 001unstated+6%—$0.15Max input: 4K tokens → 2K tokens+1cBetterF2LLM 1.7BunstatedOpen+14%——Languages: loses rucBetterF2LLM v2 14BunstatedOpen+13%——Memory (4-bit): 1.9 GB → 8.4 GBModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
Qwen 3 Embedding 8BunstatedOpen+4%—$0.01Languages: not verified+1Gemini Embedding 001unstated+6%—$0.15Max input: 4K tokens → 2K tokens+1cF2LLM 4BunstatedOpen+22%——Languages: loses ru+1cF2LLM 1.7BunstatedOpen+14%——Languages: loses rucF2LLM v2 14BunstatedOpen+13%——Memory (4-bit): 1.9 GB → 8.4 GBModelScoreCostPriceWhat changes
cF2LLM 4BunstatedOpen+22%——Languages: loses ru+1cF2LLM 1.7BunstatedOpen+14%——Languages: loses rucF2LLM v2 8BunstatedOpen+12%——Memory (4-bit): 1.9 GB → 4.5 GBcF2LLM v2 4BunstatedOpen+10%——Memory (4-bit): 1.9 GB → 2.4 GBKQZhou EmbeddingunstatedOpen+10%——Memory (4-bit): 1.9 GB → 4.2 GBRun it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceMITfree for commercial use
Benchmarks
in Embeddings & RetrievalFAQ
How much does Giga Embeddings Instruct cost?›
There is no per-unit API price: self-host only.
Is Giga Embeddings Instruct free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Giga Embeddings Instruct, and what is it best at?›
#24 of 200 in Embeddings. Strongest at: Embeddings & Retrieval.
Is Giga Embeddings Instruct better than ICT TIME And Querit Embedding v1?›
On MTEB English v2 · Clustering · English, Giga Embeddings Instruct scores 56.2 vs 56.3 — about the same.
When was Giga Embeddings Instruct released? Is there a newer version?›
Released 2025-09-23. It is the current version in its line.
Is Giga Embeddings Instruct open source?›
Yes, the weights are open (MIT licence).
Can I run Giga Embeddings Instruct locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Giga Embeddings Instruct?›
Giga Embeddings Instruct is an open-weights embeddings & retrieval model from ai-sage, released Sep 2025.
What are the best alternatives to Giga Embeddings Instruct?›
Qwen 3 Embedding 8B (better), F2LLM 4B (open weights).