// MiniCPM / VoxCPM · Embedding
MiniCPM-Embedding-Light: VRAM & local deployment
434M parameters. About 0.8 GB at 4-bit and 1.5 GB at BF16.
released 2025-01-17licence: Licence not statedmemory figures are estimates
01Specs
| Publisher | OpenBMB · openbmb |
|---|---|
| Family / series | MiniCPM / VoxCPM · MiniCPM-Embedding-Light |
| Type | Embedding (feature-extraction) |
| Parameters | 434M Source: counted from official safetensors weights |
| Released weights | BF16 · 0.9 GBdownload |
| Licence | — · Licence not statedThe model card metadata does not state a licence; check the repository files. |
| Released | 2025-01-17 (Hugging Face repo created) |
02How much VRAM it needs (estimate)
Embedding models are small; memory grows with batch size and sequence length.
| Precision | Weights | Weights + overhead | Smallest GPU | Mac |
|---|---|---|---|---|
| BF16 / FP16 (original) | 0.9 GB | 1.5 GB | 8GB GPU | Mac 16GB |
| FP8 / INT8 / Q8_0 | 0.5 GB | 1.0 GB | 8GB GPU | Mac 16GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 0.3 GB | 0.8 GB | 8GB GPU | Mac 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.
- Transformers — mentioned in the official model card
- Sentence Transformers — mentioned in the official model card
04Official repositories & quantised builds
1 official repo(s) from openbmb.
05Other MiniCPM / VoxCPM models
All 23 →| Model | Params | 4-bit total | Released |
|---|---|---|---|
| MiniCPM-V-4.7-35B-A3B | 35.2B / 3B | 24.2 GB | 2026-10-07 |
| MiniCPM-V-4.7-1B | 1.55B | 1.6 GB | 2026-10-06 |
| MiniCPM5-2B | 2.52B | 2.5 GB | 2026-09-06 |
| MiniCPM5-1B | 1.08B | 1.4 GB | 2026-05-21 |
| MiniCPM-V-4.6-Thinking | 1.3B | 1.5 GB | 2026-05-08 |
| MiniCPM-V-4.6 | 1.3B | 1.5 GB | 2026-04-13 |
| VoxCPM2 | 2.29B | 2.0 GB | 2026-04-03 |
| MiniCPM-SALA | 9.48B | 7.1 GB | 2026-02-11 |
06Sources
Data checked 2026-01-12. Parameters, context and licence are copied from the official repository; memory figures are our estimates.