Mimo GGUF models

122 GGUF models in the Mimo family, quantized by 58 uploaders. Sizes run from 35M to 1020B parameters. The longest trained context is 1024K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
MI
Mimo-V2-Flash
Mimo · unsloth
Params310B
Context256K
Q4_K_M186.8 GB
GGUF
MI
MiMo V2.6 Flash MOPD
Mimo · spiritfather
Params310B
Context1024K
Q4_K_M189.5 GB
GGUF
MI
MiMo-V2.6-Flash-RL
Mimo · YanissAmz
Params310B
Context1024K
Smallest107.8 GB
GGUF
MI
MiMo-V2.6-Flash-RL
Mimo · ggml-org
Params309B
Context1024K
Smallest1.3 GB
Vision
MI
MiMo V2.6 Flash RL NVFP4
Mimo · ProCreations
Params310B
Context1024K
Smallest4.2 GB
Coding
MI
MiMo-V2.6-Flash-MOPD
Mimo · ggml-org
Params309B
Context1024K
Smallest1.3 GB
Vision
MI
MiMo-V2.6-Pro-RL
Mimo · ggml-org
Params1020B
Context1024K
Smallest2.1 GB
Vision
MI
MiMo V2.6 Flash MOPD
Mimo · QuantaPlanta
Params310B
Context1024K
Smallest174.9 GB
Vision
MI
MiMo Negentropy 9B AGSI
Mimo · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
MI
Mimo-V2.5-Pro
Mimo · unsloth
Params1020B
Context1024K
Q4_K_M629.6 GB
Coding
MI
MiMo-V2.6-Flash-RL
Mimo · vultr
Params309B
Context1024K
Smallest2.4 GB
ReasoningTool useVision
MI
Mimo-Vl-7B-Rl
Mimo · unsloth
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
MI
MiMo V2.6 Flash RL GSQ RCO
Mimo · pfeifferj
Params309B
Context1024K
Smallest115.7 GB
GGUF
MI
Mimo-V2.5
Mimo · unsloth
Params310B
Context1024K
Q4_K_M190.9 GB
Vision
MI
mimo asr
Mimo · cstr
Params8.02B
Context—
Smallest0.0 GB
GGUF
MI
MiMo V2.6 Flash RL Mixed Quant
Mimo · Baekpica
Params310B
Context—
Smallest0.5 GB
GGUF
MI
MiMo V2.6 Flash RL UNCENSORED IQ2S Down
Mimo · BattleGhost
Params310B
Context1024K
Smallest91.7 GB
ReasoningTool use
MI
MiMo V2.6 Pro MOPD
Mimo · AesSedai
Params1020B
Context—
Smallest3.1 GB
GGUF
MI
MiMo-V2.6-Flash-MOPD
Mimo · ddh0
Params310B
Context1024K
Smallest131.4 GB
ReasoningTool useVision
MI
MiMo V2.6 Flash REAP50
Mimo · patrickbdevaney
Params157B
Context1024K
Smallest2.4 GB
ReasoningTool useVision
MI
MiMo-V2.6-Pro-MOPD
Mimo · ggml-org
Params1020B
Context1024K
Smallest2.1 GB
Vision
MI
MiMo Ornith 9B AGSI
Mimo · bartowski
Params9.2B
Context256K
Q4_K_M6.0 GB
ReasoningTool use
MI
MiMo VL 7B RL 2508
Mimo · bartowski
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
MI
MiMo 7B RL
Mimo · jedisct1
Params7.6B
Context32K
Q4_K_M4.7 GB
Reasoning
MI
MiMo Ornith 9B AGSI Abliterated HQ
Mimo · OliviaRossi
Params8.95B
Context256K
Smallest6.5 GB
Reasoning
MI
MiMo V2.5
Mimo · huihui-ai
Params310B
Context1024K
Smallest186.7 GB
ReasoningTool useVision
MI
MiMo Ornith 9B AGSI Abliterated HQ
Mimo · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
MI
MiMo V2.6 Flash MOPD
Mimo · AesSedai
Params310B
Context—
Smallest1.0 GB
GGUF
MI
MiMo V2.5
Mimo · bartowski
Params310B
Context1024K
Q4_K_M188.8 GB
Vision
MI
MiMo V2.6 Flash MOPD NVFP4
Mimo · ProCreations
Params310B
Context1024K
Smallest4.2 GB
Coding

About the Mimo GGUF models

Mimo is represented on ggufmodels.com by 122 GGUF models, quantized by 58 uploaders on Hugging Face. The most downloaded are Mimo-V2-Flash, MiMo V2.6 Flash MOPD and MiMo-V2.6-Flash-RL. Parameter counts run from 35M to 1020B, and the longest trained context window is 1024K tokens.

A Q4_K_M file of a Mimo model is between 4.7 to 629.6 GB, which is the quant most people start with. Most files come from mradermacher (27), bartowski (6) and kernelpool (5). The quants you will meet most often are Q4_K_M (53), Q8_0 (49), IQ4_XS (44) and Q3_K_M (43), where the number is how many models offer that quant.

Frequently asked questions

Which Mimo GGUF should I download?

The most downloaded Mimo GGUF here is Mimo-V2-Flash. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Mimo model need?

Q4_K_M files of Mimo models on this site range from 4.7 to 629.6 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Mimo GGUF files come from?

The most common quantizers here are mradermacher, bartowski and kernelpool. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing