mimo/Mixture of Experts

MMiMo V2 Flash 309B

Name: MiMo V2 Flash 309B
Author: mimo

chatcodingreasoningmathtool_use

309B

Parameters (15B active)

256K

Context length

Benchmarks

Quantizations

Architecture

MoE

Released

2025-12-16

Layers

KV Heads

Head Dim

192

Family

mimo

Quantization Options

Quant	Bits	VRAM	Quality
IQ2_XXS	2.38	92.4 GB	low
IQ2_M	2.93	113.7 GB	low
Q2_K	3.16	122.5 GB	low
IQ3_XXS	3.25	126.0 GB	low
IQ3_XS	3.5	135.7 GB	low
Q3_K_S	3.64	141.1 GB	low
IQ3_M	3.76	145.7 GB	low
Q3_K_M	4	155.0 GB	low
Q3_K_L	4.3	166.6 GB	moderate
IQ4_XS	4.46	172.8 GB	moderate
Q4_K_S	4.67	180.9 GB	moderate
Q4_K_M	4.89	189.4 GB	good
Q5_K_S	5.57	215.6 GB	good
Q5_K_M	5.7	220.7 GB	good
Q6_K	6.56	253.9 GB	excellent
Q8_0	8.5	328.8 GB	lossless
FP16	16	618.5 GB	lossless

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

▸ READY TO RUN THIS?RENT BY THE HOUR

RENT A GPU AND RUN MIMO V2 FLASH 309B NOW

Rent on RunPod →Or Vast.ai →

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

Community Ratings

Loading ratings...

Benchmarks (7)

AIME94.1

MMLU-PRO84.9

GPQA Diamond83.7

LiveCodeBench80.6

SWE-bench73.4

MATH-50067.7

HLE22.1

Run this model

▸Easiest way to get started·Beginners

DOCS ↗

curl -fsSL https://ollama.com/install.sh | sh

$ollama run mimo:309b-q4_K_M

Tag may need adjustment — check ollama.com/library/mimo 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

HuggingFace GGUF Downloads Build Hardware