FitMyLLM
OpenBMB/Dense

OMiniCPM-o 2.6

* [2025.06.20] ⭐️⭐️⭐️ Our official ollama repository is released. Try our latest models with one click!

chatvisionaudio
8.67B
Parameters
32K
Context length
8
Benchmarks
6
Quantizations
0
Architecture
Dense
Released
2025-01-13
Layers
28
KV Heads
4
Head Dim
128
Family
other

Quantization Options

Context length:
QuantBitsVRAM @ 16KQuality
Q4_K_M4.89
6.4 GB
5.8 + 0.7 KV
good
Q5_K_S5.57
7.2 GB
6.5 + 0.7 KV
good
Q5_K_M5.7
7.3 GB
6.7 + 0.7 KV
good
Q6_K6.56
8.3 GB
7.6 + 0.7 KV
excellent
Q8_08.5
10.4 GB
9.7 + 0.7 KV
lossless
FP1616
18.5 GB
17.8 + 0.7 KV
lossless

Select your GPU above to see speed estimates and compatibility for each quantization.

Deploying for a team or in production? Size GPUs, cost & scaling in Enterprise →
▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN MINICPM-O 2.6 NOW

Spin up an A100 / H100 / 4090 in ~60s. Pay by the second. Cancel anytime.

Community Ratings

Loading ratings...

Benchmarks (8)

MMMU85.8
MMBench80.5
IFEval68.6
BBH31.9
MMLU-PRO28.8
MATH15.2
MUSR6.6
GPQA5.3

Run this model

▸Easiest way to get started·Beginners
DOCS ↗
curl -fsSL https://ollama.com/install.sh | sh
$ollama run other:9b-q4_K_M

Tag may need adjustment — check ollama.com/library/other for available tags.

▸ SETUP GUIDE
>_

Auto-setup with fitmyllm CLI

Detects your GPU, recommends the best model, downloads it, and starts chatting — zero config. Benchmarks your speed and contributes anonymous data to improve predictions.

pip install fitmyllmthen run fitmyllmLearn more
Auto-detect GPULive tok/s in chatSpeed benchmarks9 inference engines

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

NVIDIA Tesla C2070
6 GB VRAM • 143 GB/s
NVIDIA
NVIDIA Tesla C2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla C2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla M2070
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2070-Q
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2075
6 GB VRAM • 150 GB/s
NVIDIA
NVIDIA Tesla M2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2070
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla X2090
6 GB VRAM • 177 GB/s
NVIDIA
NVIDIA Tesla K20X
6 GB VRAM • 250 GB/s
NVIDIA
NVIDIA Tesla K20Xm
6 GB VRAM • 250 GB/s
NVIDIA

Find the best GPU for MiniCPM-o 2.6

Build Hardware for MiniCPM-o 2.6
▸ SPEC SHEET

MiniCPM-o 2.6 — 8.67B Dense.

▸ SPECIFICATIONS
PARAMETERS
8.67B
ARCHITECTURE
Dense Transformer
CONTEXT LENGTH
32K tokens
CAPABILITIES
chat, vision, audio
RELEASE DATE
2025-01-13
PROVIDER
OpenBMB
FAMILY
other
▸ VRAM REQUIREMENTS
QUANTBPWVRAMQUALITY
Q4_K_M4.895.8 GB94%
Q5_K_S5.576.5 GB96%
Q5_K_M5.76.7 GB96%
Q6_K6.567.6 GB97%
Q8_08.59.7 GB100%
FP161617.8 GB100%
§ 01BENCHMARK SCORES
MMLU-PRO28.8
MATH15.2
IFEval68.6
BBH31.9
MMMU85.8
GPQA5.3
MUSR6.6
MMBench80.5
§ 03COMPATIBLE GPUs
30 @ Q4_K_M