Skip to content
English

Switch theme

// MiniCPM / VoxCPM · Embedding

MiniCPM-Embedding: VRAM & local deployment

2.73B parameters. About 2.3 GB at 4-bit and 6.5 GB at BF16.

released 2024-09-04licence: Licence not statedmemory figures are estimates

01Specs

PublisherOpenBMB · openbmb
Family / seriesMiniCPM / VoxCPM · MiniCPM-Embedding
TypeEmbedding (feature-extraction)
Parameters2.73B Source: counted from official safetensors weights
Released weightsBF16 · 5.5 GBdownload
Licence— · Licence not statedThe model card metadata does not state a licence; check the repository files.
Released2024-09-04 (Hugging Face repo created)

02How much VRAM it needs (estimate)

Embedding models are small; memory grows with batch size and sequence length.

PrecisionWeightsWeights + overheadSmallest GPUMac
BF16 / FP16 (original)5.5 GB 6.5 GB 8GB GPUMac 16GB
FP8 / INT8 / Q8_02.9 GB 3.7 GB 8GB GPUMac 16GB
4-bit (Q4_K_M / AWQ / GPTQ-Int4)1.6 GB 2.3 GB 8GB GPUMac 16GB

Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →

03How to run it

Only runtimes the publisher or the runtime’s official library names for this model.

Which inference engine to choose →

04Official repositories & quantised builds

1 official repo(s) from openbmb.

05Other MiniCPM / VoxCPM models

All 23 →
ModelParams4-bit totalReleased
MiniCPM-V-4.7-35B-A3B35.2B / 3B24.2 GB2026-10-07
MiniCPM-V-4.7-1B1.55B1.6 GB2026-10-06
MiniCPM5-2B2.52B2.5 GB2026-09-06
MiniCPM5-1B1.08B1.4 GB2026-05-21
MiniCPM-V-4.6-Thinking1.3B1.5 GB2026-05-08
MiniCPM-V-4.61.3B1.5 GB2026-04-13
VoxCPM22.29B2.0 GB2026-04-03
MiniCPM-SALA9.48B7.1 GB2026-02-11

06Sources

Data checked 2025-01-23. Parameters, context and licence are copied from the official repository; memory figures are our estimates.

Data updated: Self-host open models(UTC+8)