MiMo V2.5 Pro vs MiMo V2.6 Pro RL

MiMo V2.6 Pro RL leads llmrun Score 133.4 to 116.4; neither fits 24 GB.

Model A · Xiaomi

MiMo V2.5 Pro

116.4llmrun Score

1023.2B · 43.9B active · 1M context · MIT · Apr 2026

ChatFunctionsCode

Model B · Xiaomi

MiMo V2.6 Pro RL

133.4llmrun Score

1020B · 42B active · 1M context · MIT · Sep 2026

ChatFunctions

Which should you choose?

Choose MiMo V2.5 Pro if you want…

Also does code
MiMo V2.6 Pro RL doesn't list it

Choose MiMo V2.6 Pro RL if you want…

Higher llmrun Score
133.4 vs 116.4
Stronger at science
139.8 vs 114.6
Stronger at coding
125.7 vs 115.6
Ahead on the benchmarks
4 of 4 shared boards
Newer release
Sep 2026 vs Apr 2026

On your hardware

Each model at its default quant (Q4_K_M), a smaller one when it must. Estimates, ±20%.

MemoryMiMo V2.5 ProMiMo V2.6 Pro RL

8 GB

RTX 4060 · 8 GB tier

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

12 GB

RTX 3060 12GB · 12 GB tier

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

24 GBreference

RTX 4090 · 24 GB tier

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

32 GB

RTX 5090 · 32 GB tier

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

48 GB

RTX A6000 · 48 GB tier

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 32 GB

Mac Mini M4 · Macs

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 64 GB

Mac Studio M4 Max · Macs

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 128 GB

Mac Studio M4 Max · Macs

MiMo V2.5 Pro

Doesn't fit

smallest quant needs 283.5 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Reference GPU: RTX 4090. Tinted cell = the better pick on that machine (fits, more headroom, or at least 10% faster).

llmrun Score

with its 90% range · bars share one scale

MiMo V2.5 Pro MiMo V2.6 Pro RL

Overall

MiMo V2.5 Pro

116.4111–122

MiMo V2.6 Pro RL

133.4131–136

Coding

MiMo V2.5 Pro

115.6106–126

MiMo V2.6 Pro RL

125.7119–132

Agents

MiMo V2.5 Pro

no data

MiMo V2.6 Pro RL

132.1127–137

Science

MiMo V2.5 Pro

114.697–133

MiMo V2.6 Pro RL

139.8129–151

Reasoning

MiMo V2.5 Pro

110.8102–120

MiMo V2.6 Pro RL

no data

MiMo V2.5 Pro · #17 of 100 open models · #14 of 96 that fit ≤640 GB

MiMo V2.6 Pro RL · #1 of 100 open models · #1 of 96 that fit ≤640 GB

Benchmarks

4 shared boards: MiMo V2.5 Pro leads 0, MiMo V2.6 Pro RL leads 4 · Benchmarks imported Oct 2026

BoardMiMo V2.5 ProMiMo V2.6 Pro RL

SciCode

MiMo V2.5 Pro

50.2%#10/66 open

Lab-reportedEpoch AI

MiMo V2.6 Pro RL

60.9%#1/66 open

Lab-reportedEpoch AI · Sep 2026

ALE-Bench

MiMo V2.5 Pro

899.8#14/43 open

Lab-reportedEpoch AI

MiMo V2.6 Pro RL

1158.1#6/43 open

Lab-reportedEpoch AI · Sep 2026

CritPt

MiMo V2.5 Pro

4.0%#18/66 open

Lab-reportedEpoch AI

MiMo V2.6 Pro RL

26.6%#1/66 open

Lab-reportedEpoch AI · Sep 2026

ProofBench

MiMo V2.5 Pro

22.0%#11/26 open

Lab-reportedEpoch AI

MiMo V2.6 Pro RL

70.0%#3/26 open

Lab-reportedEpoch AI · Sep 2026

12 more boards (other shared and single-model boards)

LMArena Text

MiMo V2.5 Pro

1467.3#7/187 open

ArenaLMArena · Oct 2026

MiMo V2.6 Pro RL

1479.2#2/187 open

ArenaLMArena · Oct 2026

LMArena WebDev

MiMo V2.5 Pro

1481.3#18/52 open

ArenaLMArena · Oct 2026

MiMo V2.6 Pro RL

1624.8#5/52 open

ArenaLMArena · Oct 2026

Only MiMo V2.5 Pro (2)

DTBench84.5%
LMCA29.5%

Only MiMo V2.6 Pro RL (8)

VRAM by quantization

Memory to load the model and 2K context; below it, the total at 32K and 128K context. Lighter side in bold.

QuantMiMo V2.5 ProMiMo V2.6 Pro RL

Q2_K

MiMo V2.5 Pro

435 GB~434.9 GB file

32K 439 GB · 128K 449 GB

MiMo V2.6 Pro RL

434 GB418.8 GB file

32K 437 GB · 128K 448 GB

Q3_K_M

MiMo V2.5 Pro

499 GB459.7 GB file

32K 503 GB · 128K 513 GB

MiMo V2.6 Pro RL

498 GB~497.3 GB file

32K 501 GB · 128K 512 GB

Q4_0

MiMo V2.5 Pro

not listed

MiMo V2.6 Pro RL

511 GB~510.0 GB file

32K 514 GB · 128K 524 GB

Q4_K_M

MiMo V2.5 Pro

614 GB629.6 GB file

32K 618 GB · 128K 628 GB

MiMo V2.6 Pro RL

613 GB~612.0 GB file

32K 616 GB · 128K 626 GB

Q5_K_M

MiMo V2.5 Pro

730 GB758.0 GB file

32K 733 GB · 128K 743 GB

MiMo V2.6 Pro RL

727 GB~726.8 GB file

32K 731 GB · 128K 741 GB

Q6_K

MiMo V2.5 Pro

845 GB846.6 GB file

32K 848 GB · 128K 859 GB

MiMo V2.6 Pro RL

842 GB~841.5 GB file

32K 845 GB · 128K 856 GB

Q8_0

MiMo V2.5 Pro

1024 GB1087.6 GB file

32K 1027 GB · 128K 1038 GB

MiMo V2.6 Pro RL

1021 GB~1020.0 GB file

32K 1024 GB · 128K 1034 GB

10 more quants

IQ2_XXS

MiMo V2.5 Pro

282 GB317.2 GB file

32K 285 GB · 128K 296 GB

MiMo V2.6 Pro RL

not listed

IQ2_S

MiMo V2.5 Pro

320 GB319.4 GB file

32K 324 GB · 128K 334 GB

MiMo V2.6 Pro RL

not listed

IQ2_M

MiMo V2.5 Pro

346 GB317.3 GB file

32K 349 GB · 128K 360 GB

MiMo V2.6 Pro RL

not listed

IQ3_XXS

MiMo V2.5 Pro

397 GB412.7 GB file

32K 400 GB · 128K 411 GB

MiMo V2.6 Pro RL

not listed

IQ3_S

MiMo V2.5 Pro

435 GB377.9 GB file

32K 439 GB · 128K 449 GB

MiMo V2.6 Pro RL

not listed

IQ4_XS

MiMo V2.5 Pro

551 GB490.7 GB file

32K 554 GB · 128K 564 GB

MiMo V2.6 Pro RL

not listed

IQ4_NL

MiMo V2.5 Pro

576 GB501.3 GB file

32K 579 GB · 128K 590 GB

MiMo V2.6 Pro RL

not listed

Q4_K_S

MiMo V2.5 Pro

576 GB588.5 GB file

32K 579 GB · 128K 590 GB

MiMo V2.6 Pro RL

not listed

Q5_K_S

MiMo V2.5 Pro

704 GB713.2 GB file

32K 707 GB · 128K 718 GB

MiMo V2.6 Pro RL

not listed

BF16

MiMo V2.5 Pro

2047 GB2046.7 GB file

32K 2050 GB · 128K 2061 GB

MiMo V2.6 Pro RL

2041 GB~2040.0 GB file

32K 2044 GB · 128K 2054 GB

How to run each

MiMo V2.5 Pro

Ollama · Q4_K_M

$ollama run hf.co/unsloth/MiMo-V2.5-Pro-GGUF:Q4_K_M

All ways to run MiMo V2.5 Pro →

MiMo V2.6 Pro RL

Ollama · Q4_K_M

$ollama run hf.co/ggml-org/MiMo-V2.6-Pro-RL-GGUF

All ways to run MiMo V2.6 Pro RL →

Specifications

Specifications of MiMo V2.5 Pro and MiMo V2.6 Pro RL
Spec	MiMo V2.5 Pro	MiMo V2.6 Pro RL
Publisher	Xiaomi	Xiaomi
Parameters	1023.2B	1020B
Active parameters	44B per token	42B per token
Architecture	MiMoV2ForCausalLM	MiMoV2ForCausalLM
Context	1M tokens	1M tokens
Modalities	Chat, Function-calling, Code	Chat, Function-calling
License	MIT	MIT
Released	Apr 2026	Sep 2026

Frequently Asked Questions

Which is better, MiMo V2.5 Pro or MiMo V2.6 Pro RL?

MiMo V2.6 Pro RL leads llmrun Score 133.4 to 116.4; neither fits 24 GB. Choose MiMo V2.5 Pro for also does code; choose MiMo V2.6 Pro RL for higher llmrun Score and stronger at science.

Which needs less VRAM, MiMo V2.5 Pro or MiMo V2.6 Pro RL?

At Q4_K_M, MiMo V2.5 Pro requires 614.5 GB while MiMo V2.6 Pro RL needs 612.5 GB, making MiMo V2.6 Pro RL the easier model to run on your local setup.

Can I run MiMo V2.5 Pro or MiMo V2.6 Pro RL on a 16 GB GPU?

MiMo V2.5 Pro does not fit (smallest quant needs 283.5 GB); MiMo V2.6 Pro RL does not fit (smallest quant needs 435.6 GB).

Which has a longer context window, MiMo V2.5 Pro or MiMo V2.6 Pro RL?

MiMo V2.5 Pro supports 1,048,576 tokens and MiMo V2.6 Pro RL supports 1,048,576 tokens.