// Jina embeddings & rerankers · Embedding
jina-embeddings-v5-text-nano: VRAM & local deployment
212M parameters. About 0.6 GB at 4-bit and 1.0 GB at BF16.
released 2026-01-22licence: Non-commercialmemory figures are estimates
01Specs
| Publisher | Jina AI · jinaai |
|---|---|
| Family / series | Jina embeddings & rerankers · jina-embeddings-text-nano |
| Type | Embedding (feature-extraction) |
| Parameters | 212M Source: counted from official safetensors weights |
| Released weights | BF16 · 0.4 GBdownload |
| Licence | CC-BY-NC-4.0 · Non-commercialResearch / non-commercial licence: commercial use is not allowed without a separate agreement. |
| Released | 2026-01-22 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Embedding models are small; memory grows with batch size and sequence length.
| Precision | Weights | Weights + overhead | Smallest GPU | Mac |
|---|---|---|---|---|
| BF16 / FP16 (original) | 0.4 GB | 1.0 GB | 8GB GPU | Mac 16GB |
| FP8 / INT8 / Q8_0 | 0.2 GB | 0.7 GB | 8GB GPU | Mac 16GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 0.1 GB | 0.6 GB | 8GB GPU | Mac 16GB |
Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →
03How to run it
Only runtimes the publisher or the runtime’s official library names for this model.
- vLLM — mentioned in the official model card
- llama.cpp — mentioned in the official model card
- Transformers — mentioned in the official model card
- Sentence Transformers — mentioned in the official model card
- MLX — official MLX weights
04Official repositories & quantised builds
10 official repo(s) from jinaai.
- jina-embeddings-v5-text-nano main
- jina-embeddings-v5-text-nano-retrieval main
- jina-embeddings-v5-text-nano-classification main
- jina-embeddings-v5-text-nano-retrieval-GGUF GGUF
- jina-embeddings-v5-text-nano-text-matching main
- jina-embeddings-v5-text-nano-clustering main
- jina-embeddings-v5-text-nano-text-matching-GGUF GGUF
- jina-embeddings-v5-text-nano-classification-GGUF GGUF
- jina-embeddings-v5-text-nano-clustering-GGUF GGUF
- jina-embeddings-v5-text-nano-mlx MLX
05Other Jina embeddings & rerankers models
All 16 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| jina-reranker-v3.5 | 597M | 0.9 GB | 2026-07-14 |
| jina-embeddings-v5-omni-nano | 986M | 1.2 GB | 2026-04-01 |
| jina-embeddings-v5-omni-small | 1.63B | 1.6 GB | 2026-04-01 |
| jina-embeddings-v5-omni-nano-retrieval | 948M | 1.1 GB | 2026-03-31 |
| jina-embeddings-v5-omni-small-retrieval | 1.56B | 1.5 GB | 2026-03-31 |
| jina-embeddings-v5-text-small | 596M | 0.9 GB | 2026-01-22 |
| jina-reranker-v3 | 597M | 0.9 GB | 2025-09-18 |
| jina-code-embeddings-1.5b | 1.54B | 1.5 GB | 2025-08-26 |
06Sources
Data checked 2026-04-15. Parameters, context and licence are copied from the official repository; memory figures are our estimates.