Unlimited OCR — Hardware Requirements & GPU Compatibility
Vision
Unlimited-OCR is Baidu's 3.3-billion-parameter vision-language model for OCR and document parsing, built to extend DeepSeek-OCR's approach further. It pairs a vision encoder with a Mixture-of-Experts decoder on DeepSeek's architecture, routing to 6 of 64 experts per token plus 2 shared experts, so only about 1.1 billion parameters activate per token even though every expert must still fit in memory. Its distinguishing idea, "one-shot long-horizon parsing," extends optical context compression to longer documents processed in a single pass. It is small enough to run on a single consumer GPU once quantized. Context length is 32,768 tokens, oriented around page and document parsing. It is released under the MIT license, a highly permissive option for commercial use. Published in June 2026, it has quickly picked up community support for vLLM inference and ms-swift fine-tuning.
2.1M downloads
4.3K likesSpecifications
- Publisher
- Baidu
- Parameters
- 3.3B
- Architecture
- UnlimitedOCRForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 129,280
- Release Date
- 2026-06-19
- License
- MIT
Get Started
HuggingFace
How Much VRAM Does Unlimited OCR Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_Kest. | 3.40 | 1.8 GB | 3.7 GB | 1.42 GB | 2-bit quantization with K-quant improvements |
| Q3_K_M | 3.90 | 2.0 GB | 3.9 GB | 1.63 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 2.1 GB | 4.0 GB | 1.67 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 2.4 GB | 4.3 GB | 2.00 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 2.8 GB | 4.7 GB | 2.38 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 3.2 GB | 5.1 GB | 2.75 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 3.8 GB | 5.7 GB | 3.34 GB | 8-bit quantization, near-lossless |
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 Unlimited OCR?
Q4_K_M · 2.4 GBUnlimited OCR (Q4_K_M) requires 2.4 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 Unlimited OCR?
Q4_K_M · 2.4 GB59 devices with unified memory can run Unlimited OCR, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download Unlimited OCR
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 Unlimited OCR need?
Unlimited OCR requires 2.4 GB of VRAM at Q4_K_M, or 7.1 GB at BF16. Full 33K context adds up to 1.9 GB (4.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.3B × 4.8 bits ÷ 8 = 2 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 2.3 GB (at full 33K context)
VRAM usage by quantization
Q4_K_M2.4 GBQ4_K_M + full context4.3 GB- What's the best quantization for Unlimited OCR?
For Unlimited OCR, Q4_K_M (2.4 GB) offers the best balance of quality and VRAM usage. Q5_K_S (2.7 GB) provides better quality if you have the VRAM. The smallest option is IQ2_M at 1.6 GB.
VRAM requirement by quantization
IQ2_M1.6 GBQ3_K_M2.0 GBIQ4_NL2.3 GBQ4_K_M ★2.4 GBQ5_K_M2.8 GBBF167.1 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Unlimited OCR on a Mac?
Unlimited OCR requires at least 1.6 GB at IQ2_M, 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 Unlimited OCR locally?
Yes — Unlimited OCR can run locally on consumer hardware. At Q4_K_M quantization it needs 2.4 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Unlimited OCR?
At Q4_K_M, Unlimited OCR can reach ~389 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~519 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 ÷ 2.4 × 0.65 = ~1220 tok/s
Estimated speed at Q4_K_M (2.4 GB)
~1220 tok/s~519 tok/s~1220 tok/s~1086 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Unlimited OCR?
At Q4_K_M, the download is about 2.00 GB. The full-precision BF16 version is 6.67 GB. The smallest option (IQ2_M) is 1.13 GB.
- Which GPUs can run Unlimited OCR?
52 consumer GPUs can run Unlimited OCR at Q4_K_M (2.4 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 Unlimited OCR?
59 devices with unified memory can run Unlimited OCR at Q4_K_M (2.4 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.