Skip to content
English

Switch theme

// Jina embeddings & rerankers · Embedding

jina-colbert-v2: VRAM & local deployment

559M parameters. About 0.9 GB at 4-bit and 1.7 GB at BF16.

released 2024-08-16licence: Non-commercialmemory figures are estimates

01Specs

PublisherJina AI · jinaai
Family / seriesJina embeddings & rerankers · jina-colbert
TypeEmbedding
Parameters559M Source: counted from official safetensors weights
Released weightsBF16 · 1.1 GBdownload
LicenceCC-BY-NC-4.0 · Non-commercialResearch / non-commercial licence: commercial use is not allowed without a separate agreement.
Released2024-08-16 (Hugging Face repo created)

02How much VRAM it needs (estimate)

Embedding models are small; memory grows with batch size and sequence length.

PrecisionWeightsWeights + overheadSmallest GPUMac
BF16 / FP16 (original)1.1 GB 1.7 GB 8GB GPUMac 16GB
FP8 / INT8 / Q8_00.6 GB 1.2 GB 8GB GPUMac 16GB
4-bit (Q4_K_M / AWQ / GPTQ-Int4)0.3 GB 0.9 GB 8GB GPUMac 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.

Which inference engine to choose →

04Official repositories & quantised builds

1 official repo(s) from jinaai.

05Other Jina embeddings & rerankers models

All 16 →
ModelParams4-bit totalReleased
jina-reranker-v3.5597M0.9 GB2026-07-14
jina-embeddings-v5-omni-nano986M1.2 GB2026-04-01
jina-embeddings-v5-omni-small1.63B1.6 GB2026-04-01
jina-embeddings-v5-omni-nano-retrieval948M1.1 GB2026-03-31
jina-embeddings-v5-omni-small-retrieval1.56B1.5 GB2026-03-31
jina-embeddings-v5-text-nano212M0.6 GB2026-01-22
jina-embeddings-v5-text-small596M0.9 GB2026-01-22
jina-reranker-v3597M0.9 GB2025-09-18

06Sources

Data checked 2026-08-20. Parameters, context and licence are copied from the official repository; memory figures are our estimates.

Data updated: Self-host open models(UTC+8)