selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

MiniCPM-OCR-Jev

Side-by-side specs, memory needs, licence, runtimes and benchmarks. Add up to 4 models.

--vram
any
--gpus
--quant
--add

On your GPU

  • MiniCPM-OCR-Jev
Property
Overview
TaskOCR
Parameters2.2B
Active parametersdense
Context length256K
Input → output
Released23 Oct 2026
LicenceApache 2.0
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈5.5 GB
VRAM at Q4≈2.0 GB
VRAM at Q8≈3.1 GB
VRAM at FP16≈5.5 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days75.8K
Likes99
Runs with
Jan
KoboldCpp
llama.cpp
LM Studio
LocalAI
Ollama
SGLang
vLLM
Ollama tag—
Architecture
ArchitectureQwen3_5ForConditionalGeneration
Layers24
Attention / KV heads8 / 2
Vocabulary248 320
Weights dtypebfloat16
GGUF availableyes

Keep comparing

Memory figures are estimates for an 8K context at the chosen quantisation (Q4_K_M for LLMs by default). Speeds are rough, memory-bound estimates. Self-reported benchmark scores come from the model authors.