OpenBMB

MiniCPM-V 2.6 8B

Name: MiniCPM-V 2.6 8B
Rating: 79 (185 reviews)
Author: OpenBMB

当前

HuggingFace

138.5K下载量1.0K点赞Aug 2024发布日期2K tokens上下文Apache 2.0许可证72 优秀质量

MiniCPM-V 2.6 8B (8B parameters) requires approximately 8.6 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 10 GB of VRAM.

快速开始

— 复制粘贴即可本地运行

Copy-paste commands to run MiniCPM-V 2.6 8B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "openbmb/MiniCPM-V-2_6" \
  --hf-file "MiniCPM-V-2_6-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Quick specs

Parameters8B

Architecturedense

Context2K tokens

Modalitytext+vision

Min RAM3.1 GB

Rec. RAM4.9 GB (Q4_K_M)

LicenseApache 2.0

FamilyMiniCPM

✓ Vision✓ Chat

About this model

MiniCPM-V 2.6 is OpenBMB's compact multimodal model supporting image and video understanding alongside text. Delivers strong visual reasoning and OCR capabilities at 8B parameter scale.

快速推荐

最佳性价比A

Intel Arc B570 10GB~$219 — 45 tok/s

最佳综合S

RTX 3080 Ti 12GB~$1,199 — 112 tok/s

最佳硬件

MiniCPM-V 2.6 8B 的最佳选择

运行此模型

MiniCPM-V 2.6 8B on RTX 3080 Ti 12GB MiniCPM-V 2.6 8B on RTX 5070 12GB MiniCPM-V 2.6 8B on RTX 3080 12GB

量化选项

各量化级别的 VRAM 估算

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	3.1 GB	Low	—
Q3_K_S	3	3.9 GB	Low	—
NVFP4	4	4.5 GB	Medium	—
Q4_K_M	4	4.9 GB	Medium	—
Q5_K_M	5	5.8 GB	High	—
Q6_K	6	6.6 GB	High	—
Q8_0	8	8.6 GB	Very High	—
F16	16	16.4 GB	Maximum	—

硬件兼容性

全部硬件的适配估算

打开计算器

Computing compatibility...

内存详细分析

Reference: RTX 2060 6GB

Weights4.9 GB

KV Cache2.0 GB

Runtime1.2 GB

Headroom0.6 GB

常见问题

FAQ — MiniCPM-V 2.6 8B

另请参阅

量化指南评分方法打开计算器