MiniCPM OCR 1.0 — Hardware Requirements & GPU Compatibility
VisionFunctions
MiniCPM-OCR 1.0 is OpenBMB's 1.3-billion-parameter OCR model, the first OCR-specific model in the MiniCPM-V/o family and built on MiniCPM-V-4.6. It focuses on text-centric document understanding: text, tables, formulas, charts, seals, and structured information extraction, for Chinese and English documents including scans, photographs, skewed pages, and recaptured documents. OpenBMB also offers a DSpark speculative-decoding variant that it says improves end-to-end processing efficiency by 55%. Context length is 262,144 tokens. It is released under the Apache 2.0 license, permitting unrestricted commercial and research use, and was published in October 2026. It runs with vLLM, SGLang, llama.cpp, and Ollama, with GGUF builds available, and is small enough for any modern laptop or consumer GPU.
Runs great on a 24 GB GPU
Runs from 8 GB (Q4_K_M · 256K)Best on 24 GB (Q4_K_M · ~580 tok/s · 256K)Macs from 8 GB (Q4_K_M · ~63 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run MiniCPM OCR 1.0
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/AtomicChat/MiniCPM-OCR-1.0-GGUF:Q4_K_MQ4_K_M fits fully on the RTX 4090 · 22.5 GB free · 16K context
Download: MiniCPM-OCR-1.0-AD-Q4_K_M.gguf0.53 GBAtomicChat
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3060 12GB (10 GB headroom) · Q4_K_M
- Generation speed
- ~207 tok/s
- generation speed
- Cost per 1M output tokens
- $0.082
- per 1M output tokens
How Much VRAM Does MiniCPM OCR 1.0 Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 0.9 GB | 1.7 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 256K context · ~728 tok/s | |
| 1.0 GB | 1.7 GB | 3-bit medium — 3-bit medium quantization | Fits: 256K context · ~669 tok/s | |
| 1.0 GB | 1.8 GB | 3-bit large — 3-bit large quantization | Fits: 256K context · ~642 tok/s | |
| 1.1 GB | 1.8 GB | 4-bit small — 4-bit small quantization | Fits: 256K context · ~607 tok/s | |
| 1.1 GB | 1.9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 256K context · ~580 tok/s | |
| 1.2 GB | 2 GB | 5-bit small — 5-bit small quantization | Fits: 256K context · ~528 tok/s | |
| 1.3 GB | 2 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 256K context · ~512 tok/s | |
| 1.4 GB | 2.2 GB | 6-bit, very good — 6-bit quantization, very good quality | Fits: 256K context · ~461 tok/s | |
| 1.6 GB | 2.4 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Fits: 256K context · ~397 tok/s | |
| 3.0 GB | 3.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 256K context · ~222 tok/s |
Selected Q4_K_M
4-bit medium quantization1.5GBat 16K context
- Weights
- 0.8 GB
- KV cache
- 0.4 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 22.5 GB free · ~580 tok/s
≥50 tok/s needs ≥87 GB/s · RTX 5090 ~1031, RTX 3090 Ti ~580
Which Hardware Can Run MiniCPM OCR 1.0?
Q4_K_M · 1.1 GBMiniCPM OCR 1.0 (Q4_K_M) requires 1.1 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 2+ GB is recommended. Using the full 262K context window can add up to 6.4 GB, bringing total usage to 7.5 GB. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 163 devices with unified memory can run MiniCPM OCR 1.0, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB).
≤ 11 GB
≤ 11 GB tier →fits · 6.5 GB free · up to 256K ctx
16 GPUs · 1 Mac class · 2 device families
RTX 3080~437Simulate output on RTX 3080RTX 2080 Ti~354Simulate output on RTX 2080 TiRTX 3070 Ti~350Simulate output on RTX 3070 TiM3*8 GB~63Simulate output on iMac 24" M3 (8 GB)Orin Nano~59Simulate output on NVIDIA Jetson Orin Nano 8GB (Super)iPhone~42Simulate output on iPhone 1720 GB
fits · 18.5 GB free · up to 256K ctx
1 GPU
RX 7900 XT~425Simulate output on RX 7900 XT32–40 GB
fits · 30.5 GB free · up to 256K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~1031Simulate output on RTX 5090M5 Max36 GB~285Simulate output on Mac Studio M5 Max (36 GB)M532 GB~95Simulate output on MacBook Air 13" M5 (32 GB)Orin~118Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~78Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to MiniCPM OCR 1.0
MiniCPM family · 17 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Llama 3.2 1B InstructMeta | — | 2.3 GB | ~799 | same size |
| Inkling Small DSpark PreviewRadixArk | — | 1.5 GB | ~555 | same size |
| Sweep Next Edit 1.5BXenova | — | 1.6 GB | ~551 | same size |
| Ilama 3.2 1Bhmellor | — | 3.3 GB | ~231 | same size |
| T5gemma L L Ul2 ITGoogle | — | 4.3 GB | ~240 | same size |
| Granite 3.0 1B A400m InstructIBM | — | 1.3 GB | ~524 | same size |
Specifications
- Publisher
- OpenBMB
- Family
- MiniCPM
- Parameters
- 1.3B
- Architecture
- MiniCPMOcrForConditionalGeneration
- Context Length
- 262,144 tokens
- Vocabulary Size
- 248,100
- Release Date
- 2026-10-21
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does MiniCPM OCR 1.0 need?
MiniCPM OCR 1.0 requires 1.1 GB of VRAM at Q4_K_M, or 3.0 GB at BF16. Full 262K context adds up to 6.4 GB (7.5 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 1.3B × 4.8 bits ÷ 8 = 0.8 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 ≈ 6.7 GB (at full 262K context)
VRAM usage by quantization
What's the best quantization for MiniCPM OCR 1.0?
For MiniCPM OCR 1.0, Q4_K_M (1.1 GB) offers the best balance of quality and VRAM usage. Q5_K_S (1.2 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 0.9 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run MiniCPM OCR 1.0 on a Mac?
Yes — MacBook Air 13" M3 (8 GB) and 145 other Macs can run MiniCPM OCR 1.0. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 1.1 GB of usable unified memory (RAM minus macOS overhead).
Can I run MiniCPM OCR 1.0 locally?
Yes — MiniCPM OCR 1.0 can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is MiniCPM OCR 1.0?
At Q4_K_M, MiniCPM OCR 1.0 can reach ~4248 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~580 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 ÷ 1.13 × 0.65 = ~4602 tok/s
Estimated speed at Q4_K_M (1.1 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of MiniCPM OCR 1.0?
At Q4_K_M, the download is about 0.78 GB. The full-precision BF16 version is 2.60 GB. The smallest option (Q2_K) is 0.55 GB.
Which GPUs can run MiniCPM OCR 1.0?
52 consumer GPUs can run MiniCPM OCR 1.0 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 MiniCPM OCR 1.0?
163 devices with unified memory can run MiniCPM OCR 1.0 at Q4_K_M (1.1 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.