Jina Ocr V1 — Hardware Requirements & GPU Compatibility
Vision
jina-ocr-v1 is Jina AI's end-to-end document-parsing OCR model, built on the DeepSeek-OCR architecture. It combines a DeepEncoder vision tower, which represents a 1024x1024 page as just 256 visual tokens plus dynamic local tiles, with a 3-billion-parameter Mixture-of-Experts decoder, and adds a FastMTP speculative-decoding head that drafts several tokens at once to speed up long structured outputs. It reads documents into clean Markdown, converts equations to LaTeX and tables to HTML, and scores ahead of DeepSeek-OCR on the OmniDocBench and olmOCR-Bench document-parsing benchmarks. Its small active-parameter footprint lets it run on a single modest consumer GPU. Context length is 32,768 tokens. It is released under the CC BY-NC 4.0 license, which restricts use to non-commercial purposes. It was published in September 2026.
3.8K downloads
159 likesSpecifications
- Publisher
- jinaai
- Parameters
- 3.4B
- Architecture
- DeepseekOCRForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 129,280
- Release Date
- 2026-09-01
- License
- CC BY-NC 4.0
Get Started
HuggingFace
How Much VRAM Does Jina Ocr V1 Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 1.9 GB | 3.8 GB | 1.43 GB | 2-bit quantization with K-quant improvements |
| Q3_K_Mest. | 3.90 | 2.1 GB | 4.0 GB | 1.64 GB | 3-bit medium quantization |
| Q4_K_M | 4.80 | 2.5 GB | 4.3 GB | 2.02 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 2.8 GB | 4.7 GB | 2.40 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 3.2 GB | 5.1 GB | 2.78 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 3.8 GB | 5.7 GB | 3.37 GB | 8-bit quantization, near-lossless |
| BF16est. | 16.00 | 7.2 GB | 9.1 GB | 6.74 GB | Brain floating point 16 — preferred for training |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Jina Ocr V1?
Q4_K_M · 2.5 GBJina Ocr V1 (Q4_K_M) requires 2.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. Using the full 33K context window can add up to 1.9 GB, bringing total usage to 4.3 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Jina Ocr V1?
Q4_K_M · 2.5 GB59 devices with unified memory can run Jina Ocr V1, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download Jina Ocr V1
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Jina Ocr V1 need?
Jina Ocr V1 requires 2.5 GB of VRAM at Q4_K_M, or 7.2 GB at BF16. Full 33K context adds up to 1.9 GB (4.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.4B × 4.8 bits ÷ 8 = 2 GB
KV Cache + Overhead ≈ 0.5 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 2.3 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M2.5 GBQ4_K_M + full context4.3 GB- What's the best quantization for Jina Ocr V1?
For Jina Ocr V1, Q4_K_M (2.5 GB) offers the best balance of quality and VRAM usage. Q5_K_M (2.8 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 1.9 GB.
VRAM requirement by quantization
Q2_K1.9 GBQ4_K_M ★2.5 GBQ5_K_M2.8 GBQ6_K3.2 GBQ8_03.8 GBBF167.2 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Jina Ocr V1 on a Mac?
Jina Ocr V1 requires at least 1.9 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Jina Ocr V1 locally?
Yes — Jina Ocr V1 can run locally on consumer hardware. At Q4_K_M quantization it needs 2.5 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Jina Ocr V1?
At Q4_K_M, Jina Ocr V1 can reach ~388 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~509 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 2.5 × 0.65 = ~1213 tok/s
Estimated speed at Q4_K_M (2.5 GB)
~1213 tok/s~509 tok/s~1213 tok/s~1077 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Jina Ocr V1?
At Q4_K_M, the download is about 2.02 GB. The full-precision BF16 version is 6.74 GB. The smallest option (Q2_K) is 1.43 GB.
- Which GPUs can run Jina Ocr V1?
52 consumer GPUs can run Jina Ocr V1 at Q4_K_M (2.5 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Jina Ocr V1?
59 devices with unified memory can run Jina Ocr V1 at Q4_K_M (2.5 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.