Nanonets OCR2 3B — Hardware Requirements & GPU Compatibility
Vision
Nanonets-OCR2-3B is Nanonets' image-to-markdown OCR model, a 3.8-billion-parameter vision-language model fine-tuned from Qwen2.5-VL-3B-Instruct to turn documents into structured markdown with semantic tagging rather than plain extracted text. It converts equations into LaTeX, isolates signatures and watermarks into dedicated tags, converts form checkboxes into standard Unicode symbols, extracts complex tables as markdown or HTML, renders flow and organizational charts as Mermaid diagrams, and handles handwritten and multilingual documents across a dozen or more languages; it can also answer direct questions about a document's contents. It is an OCR and document-understanding tool rather than a general chat assistant. Its small size lets it run on a single consumer GPU. Context length is 128,000 tokens, inherited from its Qwen2.5-VL base. Nanonets has not published a specific open-source license for the model on Hugging Face. It was published in October 2025, alongside a smaller Nanonets-OCR2-1.5B-exp variant and a hosted Nanonets-OCR2-Plus service.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 125K)Best on 24 GB (Q4_K_M · ~249 tok/s · 125K)Macs from 8 GB (Q4_K_M · ~27 tok/s)
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Nanonets OCR2 3B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
ollama run hf.co/mradermacher/Nanonets-OCR2-3B-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 20.8 GB free · 16K context
Download: Nanonets-OCR2-3B.Q4_K_M.gguf1.93 GBmradermacher
Ways to runOther ways
each opens step-by-stepRun in cloud
Your own private copy · Q4_K_M · 24 GB GPU
- The easiest way to try this model
- Running in a few minutes, easy setup
- Chat right here or connect any app
$5+ bonus for new users
Runs on RTX 3080 Ti (12 GB) (8 GB headroom) · Q4_K_M
- Generation speed
- ~226 tok/s
- generation speed
- Cost per 1M output tokens
- $0.15
- per 1M output tokens
How Much VRAM Does Nanonets OCR2 3B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 2.0 GB | 3.1 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 125K context · ~333 tok/s | |
| 2.0 GB | 3.2 GB | 3-bit small — 3-bit small quantization | Fits: 125K context · ~324 tok/s | |
| 2.2 GB | 3.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 125K context · ~297 tok/s | |
| 2.3 GB | 3.4 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 125K context · ~291 tok/s | |
| 2.6 GB | 3.8 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 125K context · ~249 tok/s | |
| 3.0 GB | 4.2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 125K context · ~215 tok/s | |
| 3.5 GB | 4.6 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 125K context · ~189 tok/s | |
| 4.1 GB | 5.3 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 125K context · ~159 tok/s |
Selected Q4_K_M
4-bit medium quantization3.2GBat 16K context
- Weights
- 2.3 GB
- KV cache
- 0.6 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 20.8 GB free · ~249 tok/s
≥50 tok/s needs ≥202 GB/s · RTX 5090 ~443, RTX 3090 Ti ~249
Which Hardware Can Run Nanonets OCR2 3B?
Q4_K_M · 2.6 GBNanonets OCR2 3B (Q4_K_M) requires 2.6 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 128K context window can add up to 4.6 GB, bringing total usage to 7.3 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run Nanonets OCR2 3B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 4.8 GB free · up to 125K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~188Simulate output on RTX 3080RTX 2080 Ti~152Simulate output on RTX 2080 TiRTX 3070 Ti~150Simulate output on RTX 3070 TiM3*8 GB~27Simulate output on iMac 24" M3 (8 GB)Orin Nano~25Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~18Simulate output on iPhone 1720 GB
fits · 16.8 GB free · up to 125K ctx
1 GPU
RX 7900 XT~183Simulate output on RX 7900 XT32–40 GB
fits · 28.8 GB free · up to 125K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~443Simulate output on RTX 5090M5 Max36 GB~122Simulate output on Mac Studio M5 Max (36 GB)M532 GB~41Simulate output on MacBook Air 13" M5 (32 GB)Orin~51Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~33Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| NVIDIA Nemotron Labs Dory1.0 4B BF16NVIDIA | — | 5.7 GB | ~214 | same size |
| Granite Vision 4.1 4BIBM | — | 4 GB | ~228 | same size |
| Qwen3 4B Instruct 2507Alibaba | — | 4.2 GB | ~226 | same size |
| Phi 4 Mini ReasoningMicrosoft | — | 4.8 GB | ~228 | same size |
| Qwen2.5 VL 3B InstructAlibaba | — | 3.2 GB | ~249 | same size |
| Phi 3 Mini 4k InstructMicrosoft | — | 4.2 GB | ~193 | same size |
Specifications
- Publisher
- nanonets
- Parameters
- 3.8B
- Architecture
- Qwen2_5_VLForConditionalGeneration
- Context Length
- 128,000 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2025-10-13
Frequently Asked Questions
How much VRAM does Nanonets OCR2 3B need?
Nanonets OCR2 3B requires 2.6 GB of VRAM at Q4_K_M, or 7.9 GB at BF16. Full 128K context adds up to 4.6 GB (7.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 3.8B × 4.8 bits ÷ 8 = 2.3 GB
KV Cache + Overhead ≈ 0.3 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 5 GB (at full 128K context)
VRAM usage by quantization
What's the best quantization for Nanonets OCR2 3B?
For Nanonets OCR2 3B, Q4_K_M (2.6 GB) offers the best balance of quality and VRAM usage. Q5_K_S (3.0 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 1.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Nanonets OCR2 3B on a Mac?
Yes — Mac Mini M2 (8 GB) and 145 other Macs can run Nanonets OCR2 3B. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 2.6 GB of usable unified memory (RAM minus macOS overhead).
Can I run Nanonets OCR2 3B locally?
Yes — Nanonets OCR2 3B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Nanonets OCR2 3B?
At Q4_K_M, Nanonets OCR2 3B can reach ~1825 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~249 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 ÷ 2.63 × 0.65 = ~1977 tok/s
Estimated speed at Q4_K_M (2.6 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Nanonets OCR2 3B?
At Q4_K_M, the download is about 2.25 GB. The full-precision BF16 version is 7.51 GB. The smallest option (IQ2_XXS) is 1.03 GB.
Which GPUs can run Nanonets OCR2 3B?
52 consumer GPUs can run Nanonets OCR2 3B at Q4_K_M. 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 Nanonets OCR2 3B?
163 devices with unified memory can run Nanonets OCR2 3B at Q4_K_M (2.6 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (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.