Skip to content

MiniCPM OCR 1.0 VRAM requirements

How much VRAM MiniCPM OCR 1.0 needs
4-bit weights: 752 MBWith 8K context: 1.8 GBWith 32K context: 2.1 GB8-bit, 8K context: 2.4 GB
Parameters
1.3B
Longest context
256K
Released
Oct 2026
License
Apache 2.0
Strongest at
Reading documents

How much VRAM MiniCPM OCR 1.0 needs

Memory MiniCPM OCR 1.0 needs at each precision and context length
PrecisionWeightsWith 8KWith 32KWith 128K
16-bit2.4 GB3.5 GB3.8 GB4.9 GB
8-bit1.3 GB2.4 GB2.6 GB3.8 GB
6-bit1.0 GB2.1 GB2.3 GB3.5 GB
5-bit882 MB1.9 GB2.2 GB3.3 GB
4-bit752 MB1.8 GB2.1 GB3.2 GB
3-bit606 MB1.7 GB1.9 GB3.1 GB
2-bit465 MB1.5 GB1.8 GB2.9 GB
1.6-bit256 MB1.3 GB1.6 GB2.7 GB

One conversation, 16-bit context cache, runtime overhead included.

GPUs and Macs that run MiniCPM OCR 1.0

The best way MiniCPM OCR 1.0 runs on common GPUs, Macs and AI boxes
MachineBest fitContextSpeedFirst replyReport
RTX 40608-bit256K124 tok/s0.2 sPDF: MiniCPM OCR 1.0 on RTX 4060 report
RTX 50608-bit256K193 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 5060 report
RTX 30708-bit256K193 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 3070 report
RTX 3080 10 GB8-bit256K298 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 3080 10 GB report
RTX 3060 12 GB8-bit256K159 tok/s0.2 sPDF: MiniCPM OCR 1.0 on RTX 3060 12 GB report
Arc B5808-bit256K132 tok/s0.1 sPDF: MiniCPM OCR 1.0 on Arc B580 report
RTX 40708-bit256K213 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 4070 report
RTX 4070 Super8-bit256K213 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 4070 Super report
RTX 50708-bit256K270 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 5070 report
RTX 4060 Ti 16 GB8-bit256K130 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 4060 Ti 16 GB report
RTX 5060 Ti 16 GB8-bit256K193 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 5060 Ti 16 GB report
Arc A770 16 GB8-bit256K155 tok/s0.1 sPDF: MiniCPM OCR 1.0 on Arc A770 16 GB report
Radeon RX 9070 XT8-bit256K206 tok/s0.1 sPDF: MiniCPM OCR 1.0 on Radeon RX 9070 XT report
RTX 4070 Ti Super8-bit256K270 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 4070 Ti Super report
RTX 4080 Super8-bit256K291 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 4080 Super report
RTX 5070 Ti8-bit256K339 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 5070 Ti report
RTX 50808-bit256K356 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 5080 report
Radeon RX 7900 XTX8-bit256K275 tok/s0.1 sPDF: MiniCPM OCR 1.0 on Radeon RX 7900 XTX report
RTX 30908-bit256K350 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 3090 report
RTX 40908-bit256K370 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 4090 report
Radeon AI PRO R97008-bit256K206 tok/s0.1 sPDF: MiniCPM OCR 1.0 on Radeon AI PRO R9700 report
RTX 50908-bit256K544 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 5090 report
2× RTX 30908-bit256K350 tok/s0.1 sPDF: MiniCPM OCR 1.0 on 2× RTX 3090 report
2× RTX 40908-bit256K370 tok/s0.1 sPDF: MiniCPM OCR 1.0 on 2× RTX 4090 report
RTX PRO 5000 Blackwell 48 GB8-bit256K453 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX PRO 5000 Blackwell 48 GB report
RTX 6000 Ada8-bit256K356 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX 6000 Ada report
L40S8-bit256K329 tok/s0.1 sPDF: MiniCPM OCR 1.0 on L40S report
2× RTX 50908-bit256K544 tok/s0.1 sPDF: MiniCPM OCR 1.0 on 2× RTX 5090 report
4× RTX 30908-bit256K350 tok/s0.1 sPDF: MiniCPM OCR 1.0 on 4× RTX 3090 report
RTX PRO 6000 Blackwell8-bit256K544 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX PRO 6000 Blackwell report
Mac mini M4 16 GB8-bit256K62 tok/s1.5 sPDF: MiniCPM OCR 1.0 on Mac mini M4 16 GB report
Mac mini M4 24 GB8-bit256K62 tok/s1.5 sPDF: MiniCPM OCR 1.0 on Mac mini M4 24 GB report
Mac mini M4 32 GB8-bit256K62 tok/s1.5 sPDF: MiniCPM OCR 1.0 on Mac mini M4 32 GB report
Mac mini M4 Pro 24 GB8-bit256K122 tok/s0.8 sPDF: MiniCPM OCR 1.0 on Mac mini M4 Pro 24 GB report
Mac mini M4 Pro 48 GB8-bit256K122 tok/s0.8 sPDF: MiniCPM OCR 1.0 on Mac mini M4 Pro 48 GB report
Mac mini M4 Pro 64 GB8-bit256K122 tok/s0.8 sPDF: MiniCPM OCR 1.0 on Mac mini M4 Pro 64 GB report
M4 Max 128 GB8-bit256K187 tok/s0.4 sPDF: MiniCPM OCR 1.0 on M4 Max 128 GB report
M5 Max 128 GB8-bit256K201 tok/s0.1 sPDF: MiniCPM OCR 1.0 on M5 Max 128 GB report
M3 Ultra 96 GB8-bit256K220 tok/s0.2 sPDF: MiniCPM OCR 1.0 on M3 Ultra 96 GB report
M3 Ultra 256 GB8-bit256K220 tok/s0.2 sPDF: MiniCPM OCR 1.0 on M3 Ultra 256 GB report
M3 Ultra 512 GB8-bit256K220 tok/s0.2 sPDF: MiniCPM OCR 1.0 on M3 Ultra 512 GB report
M5 Ultra 512 GB8-bit256K269 tok/s0.1 sPDF: MiniCPM OCR 1.0 on M5 Ultra 512 GB report
Ryzen AI Max+ 395 64 GB8-bit256K97 tok/s0.2 sPDF: MiniCPM OCR 1.0 on Ryzen AI Max+ 395 64 GB report
Ryzen AI Max+ 395 128 GB8-bit256K97 tok/s0.2 sPDF: MiniCPM OCR 1.0 on Ryzen AI Max+ 395 128 GB report
RTX Spark8-bit256K135 tok/s0.1 sPDF: MiniCPM OCR 1.0 on RTX Spark report
DGX Spark8-bit256K124 tok/s0.1 sPDF: MiniCPM OCR 1.0 on DGX Spark report
Dual DGX Spark8-bit256K124 tok/s0.1 sPDF: MiniCPM OCR 1.0 on Dual DGX Spark report
DGX Station GB3008-bit256K998 tok/s0.1 sPDF: MiniCPM OCR 1.0 on DGX Station GB300 report
2× RTX PRO 6000 Blackwell8-bit256K544 tok/s0.1 sPDF: MiniCPM OCR 1.0 on 2× RTX PRO 6000 Blackwell report
4× RTX PRO 6000 Blackwell8-bit256K544 tok/s0.1 sPDF: MiniCPM OCR 1.0 on 4× RTX PRO 6000 Blackwell report
8× RTX PRO 6000 Blackwell8-bit256K544 tok/s0.1 sPDF: MiniCPM OCR 1.0 on 8× RTX PRO 6000 Blackwell report
A100 80 GB SXM8-bit256K588 tok/s0.1 sPDF: MiniCPM OCR 1.0 on A100 80 GB SXM report
H100 SXM8-bit256K759 tok/s0.1 sPDF: MiniCPM OCR 1.0 on H100 SXM report
4× H200 NVL8-bit256K879 tok/s0.1 sPDF: MiniCPM OCR 1.0 on 4× H200 NVL report
8× H200 NVL8-bit256K879 tok/s0.1 sPDF: MiniCPM OCR 1.0 on 8× H200 NVL report

Best fit is the highest quality, up to 8-bit, that leaves 16K of context. First reply is the wait for a 2K prompt. Speeds are rough, plus or minus 25%.

How to run it

llama.cpp
llama-server -hf AtomicChat/MiniCPM-OCR-1.0-GGUF
vLLM
vllm serve openbmb/MiniCPM-OCR-1.0

Questions

How much VRAM does MiniCPM OCR 1.0 need?

MiniCPM OCR 1.0 needs 752 MB for its weights at 4-bit, 1.8 GB with an 8K context and 2.1 GB with 32K. At 8-bit, 2.4 GB.

What is the minimum VRAM for MiniCPM OCR 1.0?

About 1.7 GB at 3-bit with an 8K context, the lowest precision we recommend for a model this size. The smallest machine here that runs it without spilling is the RTX 4060.

How big is MiniCPM OCR 1.0?

1.3B parameters: 2.4 GB of weights at 16-bit, 752 MB at 4-bit.

Can MiniCPM OCR 1.0 run on an RTX 4090?

Yes. At 8-bit it holds 256K of context and writes about 370 tokens a second.

More models