HunyuanOCR 1B
Tencent's 1B end-to-end OCR model that outperforms 235B general VLMs on document tasks. Engineered for edge and mobile deployment.
By Tencent · China
Updated 2026-09-15
When to pick this model
- On-device or mobile OCR with strict memory budgets
- High-throughput batch OCR where latency matters
- Receipt, invoice, and form processing at scale
- Embedded systems and edge gateways
- Cost-sensitive OCR pipelines replacing cloud APIs
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 0.8 GB |
| Q5_K_M | 1 GB |
| Q8_0 | 1.5 GB |
| FP16 (no quantization) | 2 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, HunyuanOCR 1B fits an 8 GB consumer card at Q4_K_M (0.8 GB). Stepping up to Q8_0 nearly doubles the footprint to 1.5 GB, and unquantized FP16 weights take 2 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, HunyuanOCR 1B needs roughly 3 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 50 tokens/sec on entry-level GPUs, on the order of 150 tokens/sec on a mid-range card, and up to 300 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches HunyuanOCR 1B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for HunyuanOCR 1B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | FP16 (2 GB used) |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | FP16 (2 GB used) |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | FP16 (2 GB used) |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | FP16 (2 GB used) |
| 32 GB | RTX 5090 | FP16 (2 GB used) |
Which hardware should you buy to run HunyuanOCR 1B?
To run HunyuanOCR 1B locally at Q4, you need ~0.8 GB for Q4 weights alone. Hardware option to compare: RTX 5060 Ti 16GB (ASUS Prime). Leave memory for the system and context; verify inference-engine support. A mini PC does not provide CUDA or macOS/MLX.
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Strengths
- Runs in under 1 GB VRAM at Q4
- Beats 200B+ general VLMs on document benchmarks
- End-to-end model — no separate detection/recognition stages
- Latency low enough for real-time mobile use
Limitations
- 1B ceiling shows on noisy or complex layouts
- 8k context limits multi-page workflows
- Tencent Hunyuan License is custom — review before commercial use
Typical workloads
In our catalog grid, HunyuanOCR 1B is filed under Ultra-Light OCR, Edge OCR — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: vision-language work — screenshots, charts, scanned documents.
Note the 8k-token context window — fine for short interactions, limiting for long documents or big retrieval contexts. It ships under the Tencent Hunyuan License license — commercial use is generally possible but read the specific terms before embedding it in a product.
Architecture & training
Architecture: Dense vision · 1B · Tencent Hunyuan OCR ultra-compact
Training: Tencent — text extraction from scanned documents and images, ultra-compact version.
The OCR model to pick when every megabyte counts; for messy real-world documents, step up to DeepSeek-OCR.
Quick start
Install the runtime for your system: Windows, macOS or Linux. Check the exact model tag or GGUF quantization below; catalog IDs are not necessarily Ollama tags.
Start at 4096 tokens of context, then use ollama ps to check GPU/CPU placement. A default download may use a different quantization from the configurator’s memory estimate. Keep the free setup working before considering a kit.
ollama pull hf.co/tencent/Hunyuan-OCR-1B-GGUFOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Your private ChatGPT, free, on your own machine in an hour — LM Studio, Ollama, Open WebUI, your documents, no cloud.
- Lifetime online access
- PDF + files
- 30-day refund
Similar models worth comparing
Frequently asked questions
How much VRAM does HunyuanOCR 1B need?
At the recommended Q4_K_M quantization, HunyuanOCR 1B needs about 0.8 GB of VRAM. Q8_0 takes 1.5 GB, and unquantized FP16 weights take 2 GB.
Can HunyuanOCR 1B run without a GPU?
Yes — with roughly 3 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does HunyuanOCR 1B support?
HunyuanOCR 1B supports a 8k-token context window (8,192 tokens).
Can I use HunyuanOCR 1B commercially?
HunyuanOCR 1B ships under the Tencent Hunyuan License license. Commercial use is generally permitted subject to its terms — review the license text before shipping a product.
How fast is HunyuanOCR 1B on consumer hardware?
Our compatibility engine estimates on the order of 150 tokens/sec on a mid-range GPU and up to 300 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of HunyuanOCR 1B should I download first?
Start with Q4_K_M (0.8 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It already fits an 8 GB card at FP16.