mimo/Mixture of Experts

MMiMo V2 Flash 309B

chatcodingreasoningmathtool_use
309B
Parameters (15B active)
256K
Context length
6
Benchmarks
17
Quantizations
Architecture
MoE
Released
2025-12-16
Layers
48
KV Heads
4
Head Dim
192
Family
mimo

Quantization Options

QuantBitsVRAMQuality
IQ2_XXS2.3892.4 GBlow
IQ2_M2.93113.7 GBlow
Q2_K3.16122.5 GBlow
IQ3_XXS3.25126.0 GBlow
IQ3_XS3.5135.7 GBlow
Q3_K_S3.64141.1 GBlow
IQ3_M3.76145.7 GBlow
Q3_K_M4155.0 GBlow
Q3_K_L4.3166.6 GBmoderate
IQ4_XS4.46172.8 GBmoderate
Q4_K_S4.67180.9 GBmoderate
Q4_K_M4.89189.4 GBgood
Q5_K_S5.57215.6 GBgood
Q5_K_M5.7220.7 GBgood
Q6_K6.56253.9 GBexcellent
Q8_08.5328.8 GBlossless
FP1616618.5 GBlossless

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

Benchmarks (6)

AIME94.1
MMLU-PRO84.9
GPQA Diamond83.7
LiveCodeBench80.6
SWE-bench73.4
HLE22.1

Run this model

Easiest way to get starteddocs →
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

GPUs that can run this model

At Q4_K_M quantization. Sorted by minimum VRAM.

Find the best GPU for MiMo V2 Flash 309B

Build Hardware for MiMo V2 Flash 309B

MiMo V2 Flash 309B309B Parameter Mixture of Experts LLM

Model Specifications

Parameters
309B (15B active)
Architecture
Mixture of Experts
Context Length
256K tokens
Capabilities
chat, coding, reasoning, math, tool_use
Release Date
2025-12-16
Family
mimo

VRAM Requirements

QuantizationBPWVRAMQuality
IQ2_XXS2.3892.4 GB65%
IQ2_M2.93113.7 GB75%
Q2_K3.16122.5 GB78%
IQ3_XXS3.25126.0 GB82%
IQ3_XS3.5135.7 GB84%
Q3_K_S3.64141.1 GB85%
IQ3_M3.76145.7 GB86%
Q3_K_M4155.0 GB88%
Q3_K_L4.3166.6 GB90%
IQ4_XS4.46172.8 GB92%
Q4_K_S4.67180.9 GB93%
Q4_K_M4.89189.4 GB94%
Q5_K_S5.57215.6 GB96%
Q5_K_M5.7220.7 GB96%
Q6_K6.56253.9 GB97%
Q8_08.5328.8 GB100%
FP1616618.5 GB100%

Benchmark Scores

MMLU-PRO84.9
LiveCodeBench80.6
SWE-bench73.4
AIME94.1
GPQA Diamond83.7
HLE22.1

Compatible GPUs (13)

GPUs that can run MiMo V2 Flash 309B at Q4_K_M quantization: