Inference EngineeringAcademy
HomeFoundations Free
Courses
Pricing
Resources
JobsCoding practiceStart learning

MiniCPM-V-4.6-AWQ

Checkpointopenbmb/MiniCPM-V-4.6-AWQModel card indexedModel card

Support summary

MiniCPM-V-4.6-AWQ is a checkpoint published by OpenBMB, built on the MiniCPMV4_6ForConditionalGeneration architecture. No indexed engine release, recipe, or architecture listing documents support yet. That does not mean the model is incompatible.

Configured context
262,144 tokens
License
apache-2.0
Hugging Face model card
Publisher
OpenBMB
Task
image text to text
License
apache-2.0
Library
transformers
Architecture
MiniCPMV4_6ForConditionalGeneration
Weight tensor elements
1.3B
Tensor types
I32, BF16
Quantization
awq
Configured context
262,144 tokens
Base models
openbmb/MiniCPM-V-4.6
Weight access
Public
Repository created
2026-05-09
Source 1: openbmb/MiniCPM-V-4.6-AWQ · publisher model cardSource 2: openbmb/MiniCPM-V-4.6-AWQ · Hugging Face metadataSource 3: openbmb/MiniCPM-V-4.6-AWQ · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for MiniCPM-V-4.6-AWQ
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLM0.28.0Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for vLLM 0.28.0
SGLang0.5.19Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1