MiniCPM GGUF models

637 GGUF models in the MiniCPM family, quantized by 271 uploaders. Sizes run from 4M to 34.7B parameters. The longest trained context is 512K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
MI
MiniCPM5 2B
MiniCPM · openbmb
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingTool use
MI
MiniCPM V 4.7 35B A3B
MiniCPM · openbmb
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
MI
MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking
MiniCPM · GnLOLot
Params1.08B
Context128K
Smallest1.2 GB
ReasoningTool use
MI
MiniCPM5 1B Claude Opus Fable5 Thinking
MiniCPM · GnLOLot
Params1.08B
Context128K
Q4_K_M0.7 GB
Reasoning
MI
MiniCPM V 4.7 35B A3B Uncensored
MiniCPM · AtomicChat
Params34.7B
Context256K
Smallest0.1 GB
GGUF
MI
MiniCPM V 4.7 1B
MiniCPM · openbmb
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningTool useVision
MI
MiniCPM o 4 5
MiniCPM · openbmb
Params8.2B
Context40K
Q4_K_M5.0 GB
Vision
MI
MiniCPM5 1B
MiniCPM · openbmb
Params1.08B
Context128K
Q4_K_M0.7 GB
Tool use
MI
MiniCPM V 4 5
MiniCPM · openbmb
Params8.2B
Context40K
Q4_K_M5.0 GB
CodingVision
MI
MiniCPM V 4.7 35B A3B CRACKv5 2p0
MiniCPM · dealignai
Params34.7B
Context256K
Q4_K_M22.6 GB
Vision
MI
MiniCPM-V-4.7-35B-A3B
MiniCPM · AtomicChat
Params34.7B
Context256K
Smallest10.1 GB
ReasoningTool useVision
MI
MiniCPM V 4.7 35B A3B DSpark
MiniCPM · openbmb
Params389M
Context256K
Q4_K_M0.2 GB
Tool useVision
MI
MiniCPM-V-4.7-35B-A3B-Uncensored
MiniCPM · gbuzhf
Params34.7B
Context256K
Smallest11.9 GB
Vision
MI
MiniCPM V 4_6
MiniCPM · openbmb
Params752M
Context256K
Q4_K_M0.5 GB
Vision
MI
MiniCPM5 2B LocalAI
MiniCPM · weareapexcreators
Params2.52B
Context128K
Smallest2.7 GB
GGUF
MI
MiniCPM OCR 1.0
MiniCPM · openbmb
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
MI
MiniCPM V 4.7 1B DSpark
MiniCPM · openbmb
Params214M
Context256K
Q4_K_M0.1 GB
Tool useVision
MI
MiniCPM-V-4.7-1B
MiniCPM · AtomicChat
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningTool useVision
MI
MiniCPM V 2 6
MiniCPM · openbmb
Params7.61B
Context32K
Q4_K_M4.7 GB
Vision
MI
MiniCPM V 4.7 35B A3B
MiniCPM · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
MI
MiniCPM5 2B heretic abliterated
MiniCPM · Abiray
Params2.52B
Context128K
Q4_K_M1.6 GB
GGUF
MI
MiniCPM V 4.7 1B abliterated heretic
MiniCPM · Abiray
Params1.01B
Context256K
Q4_K_M0.7 GB
Vision
MI
Sharp MiniCPM5 2B
MiniCPM · peculiar-ragdoll
Params2.52B
Context—
Smallest0.0 GB
GGUF
MI
MiniCPM5 2B
MiniCPM · bartowski
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingTool use
MI
MiniCPM V 4.7 1B LocalAI
MiniCPM · weareapexcreators
Params1.01B
Context256K
Smallest1.1 GB
Vision
MI
MiniCPM5 2B Math
MiniCPM · Caldalis
Params2.52B
Context128K
Q4_K_M1.6 GB
Reasoning
MI
MiniCPM V 4.7 1B heretic
MiniCPM · saidutta69
Params1.01B
Context256K
Q4_K_M0.7 GB
ReasoningRoleplayTool use
MI
MiniCPM5 2B Abliterated Uncensored
MiniCPM · mondk
Params2.52B
Context128K
Q4_K_M1.6 GB
Tool use
MI
MiniCPM OCR Jev
MiniCPM · openbmb
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
MI
MiniCPM V Apps
MiniCPM · tc-mb
Params912M
Context256K
Q4_K_M0.5 GB
Vision

About the MiniCPM GGUF models

MiniCPM is represented on ggufmodels.com by 637 GGUF models, quantized by 271 uploaders on Hugging Face. The most downloaded are MiniCPM5 2B, MiniCPM V 4.7 35B A3B and MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking. Parameter counts run from 4M to 34.7B, and the longest trained context window is 512K tokens.

A Q4_K_M file of a MiniCPM model is between 0.0 to 22.6 GB, which is the quant most people start with. Most files come from mradermacher (132), openbmb (24) and tinyopsec (17). The quants you will meet most often are Q4_K_M (434), Q8_0 (340), Q5_K_M (301) and Q6_K (296), where the number is how many models offer that quant.

Frequently asked questions

Which MiniCPM GGUF should I download?

The most downloaded MiniCPM GGUF here is MiniCPM5 2B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a MiniCPM model need?

Q4_K_M files of MiniCPM models on this site range from 0.0 to 22.6 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do MiniCPM GGUF files come from?

The most common quantizers here are mradermacher, openbmb and tinyopsec. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing