// Open-model VRAM table · family
Jina embeddings & rerankers: local deployment & VRAM
16 open-weight models from Jina AI (54 official repos incl. quantised builds).
official orgs: jinaailatest 2026-07-14memory = estimate
01Embedding (12)
| Model | Params | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|
| jina-embeddings-v5-omni-nano | 986M | 2.7 GB | 1.2 GB | 8GB GPU | Mac 16GB | Non-commercial | 2026-04-01 |
| jina-embeddings-v5-omni-small | 1.63B | 4.1 GB | 1.6 GB | 8GB GPU | Mac 16GB | Non-commercial | 2026-04-01 |
| jina-embeddings-v5-omni-nano-retrieval | 948M | 2.6 GB | 1.1 GB | 8GB GPU | Mac 16GB | Non-commercial | 2026-03-31 |
| jina-embeddings-v5-omni-small-retrieval | 1.56B | 3.9 GB | 1.5 GB | 8GB GPU | Mac 16GB | Non-commercial | 2026-03-31 |
| jina-embeddings-v5-text-nano | 212M | 1.0 GB | 0.6 GB | 8GB GPU | Mac 16GB | Non-commercial | 2026-01-22 |
| jina-embeddings-v5-text-small | 596M | 1.8 GB | 0.9 GB | 8GB GPU | Mac 16GB | Non-commercial | 2026-01-22 |
| jina-code-embeddings-1.5b | 1.54B | 3.9 GB | 1.5 GB | 8GB GPU | Mac 16GB | Non-commercial | 2025-08-26 |
| jina-code-embeddings-0.5b | 494M | 1.6 GB | 0.8 GB | 8GB GPU | Mac 16GB | Non-commercial | 2025-08-19 |
| jina-embeddings-v4-vllm-retrieval | 3.75B | 8.8 GB | 3.0 GB | 8GB GPU | Mac 16GB | Licence not stated | 2025-07-01 |
| jina-embeddings-v4 | 3.75B | 8.8 GB | 3.0 GB | 8GB GPU | Mac 16GB | Licence not stated | 2025-05-07 |
| jina-embeddings-v3 | 572M | 1.8 GB | 0.9 GB | 8GB GPU | Mac 16GB | Non-commercial | 2024-09-05 |
| jina-colbert-v2 | 559M | 1.7 GB | 0.9 GB | 8GB GPU | Mac 16GB | Non-commercial | 2024-08-16 |
02Reranker (4)
| Model | Params | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|
| jina-reranker-v3.5 | 597M | 1.8 GB | 0.9 GB | 8GB GPU | Mac 16GB | Non-commercial | 2026-07-14 |
| jina-reranker-v3 | 597M | 1.8 GB | 0.9 GB | 8GB GPU | Mac 16GB | Non-commercial | 2025-09-18 |
| jina-reranker-m0 | 2.44B | 5.9 GB | 2.1 GB | 8GB GPU | Mac 16GB | Non-commercial | 2025-03-27 |
| jina-reranker-v2-base-multilingual | 278M | 1.1 GB | 0.7 GB | 8GB GPU | Mac 16GB | Non-commercial | 2024-06-19 |
03Other families
Qwen · IBM Granite · NVIDIA Nemotron · Gemma · Mistral / Magistral / Devstral · GLM / CogVideoX (Z.ai) · DeepSeek · Ai2 OLMo / Molmo · Ant Ling / Ring / Ming · Liquid LFM · MiniCPM / VoxCPM · Tencent Hunyuan / Hy · Phi · Llama · Meituan LongCat · Wan · Kimi · Cohere Command / Aya · Xiaomi MiMo · FLUX · Microsoft VibeVoice / Fara / Harrier · InternLM / Intern-S · StepFun Step · MiniMax · Baidu ERNIE · NVIDIA Parakeet / Canary speech · Stable Diffusion / Stable Audio · Yi (01.AI) · ByteDance Seed · SmolLM / SmolVLM · BGE embeddings & rerankers · LTX Video · FunAudioLLM speech · gpt-oss · poolside Laguna · Whisper · Baichuan · Thinking Machines Inkling · xAI Grok · rednote dots
Totals include 10% + 0.5GB overhead and one 8K-token KV cache for text models. Estimates only. Method →