// MiniCPM / VoxCPM · Vision-language
MiniCPM-V-2_6: VRAM & local deployment
8.1B parameters. About 5.9 GB at 4-bit and 18.3 GB at BF16.
released 2024-08-04licence: Licence not statedmemory figures are estimates
01Specs
| Publisher | OpenBMB · openbmb |
|---|---|
| Family / series | MiniCPM / VoxCPM · MiniCPM-V-2_6 |
| Type | Vision-language (image-text-to-text) |
| Parameters | 8.1B Source: counted from official safetensors weights |
| Context length | — |
| Released weights | BF16 · 16.2 GBdownload |
| Licence | — · Licence not statedThe model card metadata does not state a licence; check the repository files. |
| Released | 2024-08-04 (Hugging Face repo created) |
| Access | Gated: accept the licence on Hugging Face before downloading. |
02How much VRAM it needs (estimate)
Total = weights + 10% + 0.5GB overhead + KV cache for one request (FP16 KV). More concurrent users multiply the KV column.
| Precision | Weights | Smallest GPU | Mac |
|---|---|---|---|
| BF16 / FP16 (original) | 16.2 GB | RTX 4090 24GB | Mac 36GB |
| FP8 / INT8 / Q8_0 | 8.6 GB | 12GB GPU | Mac 24GB |
| 4-bit (Q4_K_M / AWQ / GPTQ-Int4) | 4.9 GB | 8GB GPU | Mac 16GB |
KV cache not estimated: the official config.json is gated or lacks attention parameters. Totals above are weights + overhead only.
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.
- vLLM — mentioned in the official model card
- llama.cpp — mentioned in the official model card
- Ollama — mentioned in the official model card
- Transformers — mentioned in the official model card
04Official repositories & quantised builds
4 official repo(s) from openbmb.
- MiniCPM-V-2_6 main
- MiniCPM-V-2_6-gguf GGUF
- MiniCPM-V-2_6-int4 INT4
- MiniCPM-V-2_6-GPTQ GPTQ
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 2025-06-13. Parameters, context and licence are copied from the official repository; memory figures are our estimates.