Inkling vs MiMo V2.6 Pro RL

MiMo V2.6 Pro RL leads llmrun Score 133.4 to 116.0; neither fits 24 GB.

Model A · Thinking Machines

Inkling

116.0llmrun Score

952.4B · 18.1B active · Apache 2.0 · Jul 2026

VisionChatFunctions

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 Inkling if you want…

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

Choose MiMo V2.6 Pro RL if you want…

Higher llmrun Score
133.4 vs 116.0
Stronger at science
139.8 vs 116.4
Stronger at agents
132.1 vs 111.4
Ahead on the benchmarks
8 of 8 shared boards

On your hardware

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

MemoryInklingMiMo V2.6 Pro RL

8 GB

RTX 4060 · 8 GB tier

Inkling

Doesn't fit

smallest quant needs 408.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

12 GB

RTX 3060 12GB · 12 GB tier

Inkling

Doesn't fit

smallest quant needs 408.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

16 GB

RTX 5060 Ti 16GB · 16 GB tier

Inkling

Doesn't fit

smallest quant needs 408.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

24 GBreference

RTX 4090 · 24 GB tier

Inkling

Doesn't fit

smallest quant needs 408.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

32 GB

RTX 5090 · 32 GB tier

Inkling

Doesn't fit

smallest quant needs 408.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

48 GB

RTX A6000 · 48 GB tier

Inkling

Doesn't fit

smallest quant needs 408.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 32 GB

Mac Mini M4 · Macs

Inkling

Doesn't fit

smallest quant needs 408.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 64 GB

Mac Studio M4 Max · Macs

Inkling

Doesn't fit

smallest quant needs 408.4 GB

MiMo V2.6 Pro RL

Doesn't fit

smallest quant needs 435.6 GB

Mac 128 GB

Mac Studio M4 Max · Macs

Inkling

Doesn't fit

smallest quant needs 408.4 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

Inkling MiMo V2.6 Pro RL

Overall

Inkling

116.0114–118

MiMo V2.6 Pro RL

133.4131–136

Coding

Inkling

110.2105–115

MiMo V2.6 Pro RL

125.7119–132

Agents

Inkling

111.4102–120

MiMo V2.6 Pro RL

132.1127–137

Math

Inkling

112.1107–117

MiMo V2.6 Pro RL

no data

Science

Inkling

116.4106–127

MiMo V2.6 Pro RL

139.8129–151

Reasoning

Inkling

121.0118–124

MiMo V2.6 Pro RL

no data

Inkling · #18 of 100 open models · #15 of 96 that fit ≤640 GB

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

Benchmarks

8 shared boards: Inkling leads 0, MiMo V2.6 Pro RL leads 8 · Benchmarks imported Oct 2026

BoardInklingMiMo V2.6 Pro RL

SciCode

Inkling

47.0%#18/66 open

Lab-reportedEpoch AI · Jul 2026

MiMo V2.6 Pro RL

60.9%#1/66 open

Lab-reportedEpoch AI · Sep 2026

ALE-Bench

Inkling

946.0#11/43 open

Lab-reportedEpoch AI · Jul 2026

MiMo V2.6 Pro RL

1158.1#6/43 open

Lab-reportedEpoch AI · Sep 2026

APEX-Agents

Inkling

33.8%#12/16 open

Lab-reportedEpoch AI · Jul 2026

MiMo V2.6 Pro RL

59.5%#1/16 open

Lab-reportedEpoch AI · Sep 2026

CritPt

Inkling

5.4%#16/66 open

Lab-reportedEpoch AI · Jul 2026

MiMo V2.6 Pro RL

26.6%#1/66 open

Lab-reportedEpoch AI · Sep 2026

LiveBench 2026 Coding

Inkling

64.0#9/15 open

IndependentLiveBench · Sep 2026

MiMo V2.6 Pro RL

81.5#4/15 open

IndependentLiveBench · Sep 2026

LiveBench 2026 Long-Horizon

Inkling

14.1#11/15 open

IndependentLiveBench · Sep 2026

MiMo V2.6 Pro RL

47.5#1/15 open

IndependentLiveBench · Sep 2026

LiveBench 2026 Reasoning

Inkling

78.3#9/15 open

IndependentLiveBench · Sep 2026

MiMo V2.6 Pro RL

79.6#7/15 open

IndependentLiveBench · Sep 2026

ProofBench

Inkling

0.0%#26/26 open

Lab-reportedEpoch AI · Jul 2026

MiMo V2.6 Pro RL

70.0%#3/26 open

Lab-reportedEpoch AI · Sep 2026

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

LMArena Text

Inkling

1440.9#20/187 open

ArenaLMArena · Oct 2026

MiMo V2.6 Pro RL

1479.2#2/187 open

ArenaLMArena · Oct 2026

LMArena WebDev

Inkling

1413.7#26/52 open

ArenaLMArena · Oct 2026

MiMo V2.6 Pro RL

1624.8#5/52 open

ArenaLMArena · Oct 2026

LiveBench 2026 Browser

Inkling

16.0#8/15 open

IndependentLiveBench · Sep 2026

MiMo V2.6 Pro RL

88.0#1/15 open

IndependentLiveBench · Sep 2026

LiveBench 2026 Data Analysis

Inkling

72.8#8/15 open

IndependentLiveBench · Sep 2026

MiMo V2.6 Pro RL

72.3#9/15 open

IndependentLiveBench · Sep 2026

LiveBench 2026 Design

Inkling

58.3#14/15 open

IndependentLiveBench · Sep 2026

MiMo V2.6 Pro RL

78.5#1/15 open

IndependentLiveBench · Sep 2026

LiveBench 2026 Research

Inkling

59.9#11/15 open

IndependentLiveBench · Sep 2026

MiMo V2.6 Pro RL

76.7#4/15 open

IndependentLiveBench · Sep 2026

Only Inkling (17)

VRAM by quantization

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

QuantInklingMiMo V2.6 Pro RL

Q2_K

Inkling

405 GB~404.8 GB file

32K 412 GB · 128K 432 GB

MiMo V2.6 Pro RL

434 GB418.8 GB file

32K 437 GB · 128K 448 GB

Q3_K_M

Inkling

465 GB~464.3 GB file

32K 471 GB · 128K 491 GB

MiMo V2.6 Pro RL

498 GB~497.3 GB file

32K 501 GB · 128K 512 GB

Q4_0

Inkling

not listed

MiMo V2.6 Pro RL

511 GB~510.0 GB file

32K 514 GB · 128K 524 GB

Q4_K_M

Inkling

572 GB~571.4 GB file

32K 578 GB · 128K 598 GB

MiMo V2.6 Pro RL

613 GB~612.0 GB file

32K 616 GB · 128K 626 GB

Q5_K_M

Inkling

679 GB~678.6 GB file

32K 686 GB · 128K 705 GB

MiMo V2.6 Pro RL

727 GB~726.8 GB file

32K 731 GB · 128K 741 GB

Q6_K

Inkling

786 GB~785.7 GB file

32K 793 GB · 128K 813 GB

MiMo V2.6 Pro RL

842 GB~841.5 GB file

32K 845 GB · 128K 856 GB

Q8_0

Inkling

953 GB856.8 GB file

32K 959 GB · 128K 979 GB

MiMo V2.6 Pro RL

1021 GB~1020.0 GB file

32K 1024 GB · 128K 1034 GB

1 more quant

BF16

Inkling

1905 GB1894.3 GB file

32K 1912 GB · 128K 1932 GB

MiMo V2.6 Pro RL

2041 GB~2040.0 GB file

32K 2044 GB · 128K 2054 GB

How to run each

Inkling

Ollama · Q4_K_M

$ollama run hf.co/unsloth/inkling-GGUF

All ways to run Inkling →

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 Inkling and MiMo V2.6 Pro RL
Spec	Inkling	MiMo V2.6 Pro RL
Publisher	Thinking Machines	Xiaomi
Parameters	952.4B	1020B
Active parameters	18B per token	42B per token
Architecture	InklingForConditionalGeneration	MiMoV2ForCausalLM
Context	—	1M tokens
Modalities	Vision, Chat, Function-calling	Chat, Function-calling
License	Apache 2.0	MIT
Released	Jul 2026	Sep 2026

Frequently Asked Questions

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

MiMo V2.6 Pro RL leads llmrun Score 133.4 to 116.0; neither fits 24 GB. Choose Inkling for also does vision; choose MiMo V2.6 Pro RL for higher llmrun Score and stronger at science.

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

At Q4_K_M, Inkling requires 572.1 GB while MiMo V2.6 Pro RL needs 612.5 GB, making Inkling the easier model to run on your local setup.

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

Inkling does not fit (smallest quant needs 408.4 GB); MiMo V2.6 Pro RL does not fit (smallest quant needs 435.6 GB).